Six Sigma PDF

Six Sigma Green Belt Certification
Module 0 – Certification Exam and Course Overview

Module 0 – Certification Process
Outline
!   What is a Six Sigma Green Belt
!   ASQ Green Belt exam
!   Structure of this course
Module 0 2
What is a Six Sigma Green Belt
!  Analyzes and solves quality problems using Six Sigma
tools and processes
!  Does not lead Six Sigma projects
!  Supports or operates under a Black Belt
!  Six Sigma activities usually part time
!  Has passed the ASQ Green Belt exam
Module 0 3
ASQ Green Belt Exam
!  Fee is $359 or $209 for ASQ members
!  Apply on ASQ's Web site
!  Based on the ASQ Green Belt Body of Knowledge
http://asq.org/cert/six-sigma-green-belt/bok
!  Bring #2 pencils
Module 0 5
ASQ Green Belt Exam (cont'd)
!  100 Questions with 4 hours to complete
!  Pass is 80%
!  Open book
!  Your own notes are allowed, however the proctor will
inspect your notes and can reject them
!  No collections of questions and answers are allowed
!  Hand held calculators without an alphabetic keyboard
are allowed. The memory must be cleared
Module 0 6
ASQ Green Belt Exam Content
Version instituted on Dec 6, 2014
!  Overview of Six Sigma and the Organization (13
questions)
!  Six Sigma Define (23 questions)
!  Six Sigma Measure (23 questions)
!  Six Sigma – Analyze (15 questions)
!  Six Sigma – Improve (15 questions)
!  Six Sigma – Control (11 questions)
Module 0 7
ASQ Green Belt Exam Content (Cont'd)
As it is an open book exam, simple memorization of
definitions and formulas will not get a you a pass. You will
need to be able to understand the material in sufficient
detail to enable you to successfully determine the answer
by;
!  Evaluating,
!  Analyzing,
!  Applying, and
!  Creating
Module 0 8
This Course
!  The course is divided into sections corresponding to the exam
!  The final section will be devoted to exam tips and trap,
suggested reading as well as 'night before' cram session
!  It is expected that you understand statistical and mathematical
symbol, have a knowledge of basic statistics, and preferably
are already familiar with the Greenbelt Body of Knowledge
Module 0 9
This Course
!  As the exam is open book, the focus is on the concepts, not
the formulas
Module 0 10
End of Module 0 – Certification Process
In this module we covered;
!   What is a Six Sigma Green Belt
!   ASQ Green Belt exam
!   Structure of this course
Module 0 11
Module 1 - Six Sigma and the Organization
Module 1 Topics
1. Six Sigma and Organizational Goals
1. Value of Six Sigma
2. Organizational Goals and Six Sigma Projects
3. Organizational Drivers and Metrics
2. Lean Principles in the Organization

1. Lean concepts
2. Value-added and non-value-added activities
3. Design for Six Sigma (DFSS)

1. Road map for DFSS
2. Basic failure mode and effects analysis (FMEA)
3. Design FMEA and Process FMEA
Module 1 13
Six Sigma and Organizational Goals
Value of Six Sigma
This section will describe;
1. The origins of Six Sigma,
2. Its goals and philosophy,
3. Why organizations use Six Sigma, and
4. How processes, inputs, outputs, and feedback affect the organization.
Module 1 14
Value of Six Sigma – What is Six Sigma
But first, lets remind ourselves what is Six Sigma;
!  The Greek letter Sigma ( σ ) represents Standard Deviation, so Six Sigma literally
translates to six standard deviations
!  Best defined as an ‘systematic data-driven approach that seeks to find and
eliminate causes of mistakes or defects in business processes by focusing on
outputs that are critical importance to customers
!  It encompasses;
!  Business Strategy based on a philosophy of operational excellence
!  Tools and tactics for process measurement and management
Module 1 15
Value of Six Sigma - The origins of Six Sigma
!  Six Sigma was first developed in the late 1980s at Motorola in response to their
struggle to meet the demanding quality targets for complex manufactured products.
!  Become widely known when Jack Welsh GE adopted it in 1994
!  Initially it was a quality measurement approach based on statistical principles
!  Then it transformed to a disciplined process improvement technique based on
reducing variation within the system with the help of a number of statistical tools
Roots lie in the works of Phillip B. Crosby, George D. Edwards, W. Edward Deming,
Walter Andrew Shewhart, Armand V. Feigenbaum, Joseph M. Juran, Kaoru Ishikawa ,
and Genichi Taguchi
Module 1 16
Phillip B. Crosby
Author of Quality is Free, one of the seminal texts of quality control
! 
Extolled the benefits of doing things right the first time

! 
Four cardinal rules of quality management:

! 
1.  the performance standard should be set as zero defects;

2.  quality is the same thing as conformance to requirements;
3.  quality is achieved by preventing defects;
4.  and the measure of quality’s value is the cost of nonconformance.
Module 1 17
George D. Edwards
!  First president of the American Society for Quality
!  Head of the inspection engineering department for Bell Telephone Laboratories
!  Instrumental in advancing Bell Lab's groundbreaking quality assurance program.
Module 1 18
W. Edwards Deming
!  One of the fathers of quality control
!  Key insight was the use of statistics for quality control
!  Another insight was the difference between common- and special-cause variation
!  Best know for defining the “seven deadly diseases of the workplace” and “14 points
for management.”
Module 1 19
Deming's seven deadly diseases of the workplace;
1.  Lack of consistency in planning
2.  Emphasis on short-term profits
3.  Poor performance evaluation systems
4.  Excessive turnover among employees
5.  Overreliance on the metrics that are the easiest to obtain
6.  Excessive medical costs
7.  Excessive liability costs
Module 1 20
Deming's 14 points for management;
1. Maintain consistent purposes 8. Eliminate fear
2. Adapt a new philosophy 9. Reduce interdepartmental barriers
3. Eliminate dependence on inspection 10. Reduce pressure on the workforce and eliminate
quotas
4. Cease to award business based on price alone 11. Eliminate ineffective management styles
5. Constant quality improvement 12. Promote employee pride
6. Provide on-the-job training for employees 13. Institute a vigorous program of education and
self-improvement
7. Establish leadership Module 1 21

14. The transformation is everybody's job
Walter Andrew Shewhart;
1.  The father of statistical quality control
2.  Formulate the statistical idea of tolerance intervals and to propose his data
presentation rules, which are listed below:
–  Data has no meaning apart from its context.
–  Data contain both signal and noise. To be able to extract information, one
must separate the signal from the noise within the data.
3.  Originated the Plan-Do-Check-Act cycle popularized by Deming
4.  Long-time collaboration with Deming, who championed Shewhart's ideas
Module 1 22
Armand V. Feigenbaum;
1.  Promoter of TQM
2.  Known for his 9 M's of quality; markets, management, men, money, motivation,
materials, machines, modern information sources, and mounting (constantly
improving) product requirements.
3.  One of the first to insist that the customer's perspective be used to assess quality
Module 1 23
Joseph M. Juran;
1.  Known for his three main components of quality management;
1.  Use of statistical quality control
2.  Quality improvement
3.  Quality planning
2.  Also one of the first to insist that the customer's perspective be used to assess
quality
3.  Advocated deep management involvement in the quality improvement process
Module 1 24
Kaoru Ishikawa ;
1.  Developed the Ishikawa or fish diagram for root cause analysis
2.  Major advocate of TQM and developed Quality Circles
Genichi Taguchi
1. Another advocate of TQM in Japan
2. Promoted the use of statistics in quality management
3.Wrote The Design of Experiments
Module 1 25
Value of Six Sigma – Goals, Principals, and
Philosophy
The Fundamental Principals of Six Sigma are:
Y=f(X) + ε: All outcomes and results (the Y) are determined by inputs (the Xs) with
! 
some degree of uncertainty (ε)

To change or improve results (the Y), you have to focus on the inputs (the Xs), modify
! 
them, and control them

Variation is everywhere, and it degrades consistent, good performance. Your mission
! 
is to find it and minimize it!

Valid measurements and data are required foundations for consistent, breakthrough
! 
improvement
Only a critical few inputs have significant effect on the output. Concentrate on the
! 
critical few
Every decision and conclusion has risk (ε), which must be weighed against the
! 
context of the decision

Module 1 26
Value of Six Sigma – Goals, Principals and
Philosophy
The philosophy of Six Sigma:
Defects are expensive; both in resources and in customer satisfaction
! 
Competitive Advantage is gained by meeting customer expectations

! 
Focus on processes
! 
Strong alignment to organizational goals

! 
Reducing process output variation to stay within the limits defined by the customer
! 
will yield significant returns.

Therefor, continuous improvement of an organization's processes is pursued via data
! 
analysis and the application of specific variance-reduction techniques
Module 1 27
Value of Six Sigma – Goals and Philosophy
By utilizing Six Sigma to identify and optimize the vital few variables impacting quality
and throughput, an organization can realize sustainable breakthrough performance.
Module 1 28
Organizational Drivers and Metrics
What are the key Organizational Drivers? In general they are;
!  Profit
!  Market Share
!  Customer Satisfaction
!  Efficiency
!  Product Differentiation
While quality is not mentioned above, it is key to successfully delivering on the above
drivers.
Take profit for example; a non-Six Sigma company typically spends 25%-40% of its
revenues fixing problems. Whereas Six Sigma companies typically spend less than 5
percent of their revenues fixing problems
Module 1 29
In order to both understand where an organization is and how it is progressing, on
needs quantifiable metrics to baseline and to track progress.
The selected metrics must map back to the organizational drivers and will measure
! 
process and financial performance

These metrics must be relevant to the problem or goal in mind.
! 
All roads lead back to the concept of the Cost of Quality

! 
There are widely-used financial metrics as well as balanced scorecards

! 
Six Sigma also provides us with a set of key metrics

! 
Module 1 30
Key Six Sigma Metrics;
DPU – Defects Per Unit
! 
DPO – Defects Per Opportunity

! 
DPMO – Defects Per Million Opportunities

! 
FTY – First Pass Yield

! 
TPY – Throughput Yield

! 
FY – Final Yield
! 
RTY – Rolled Throughput Yield

! 
Cycle Time
! 
Takt Time
! 
To be covered in detail later in the course

Module 1 31
Key Financial Metrics;
Return on Investment (ROI) = (Net Profit/ Investment) × 100
! 
Return on Assets (ROA) = Net Income /Average Total Assets

! 
Net Present Value (NPV) = Each cash inflow/outflow is discounted back to its present
! 
value (PV). Then they are summed to give the NPV.

Where t is the time of the cashflow, i is the discount rate
Rt is the net cashflow at time
! Internal Rate of Return (IRR) - the annualized effective compounded rate of return
Module 1 32
Balanced Scorecard;
Many Six Sigma professionals advocate the use of balanced scorecard metrics as a
method for ensuring that the project meets both customer and business needs.
The balanced scorecard approach includes;
Financial and non-financial metrics,
! 
Lagging and leading measures

! 
Across the following four areas:

! 
!  financial,
!  customer,
!  internal processes,
!  and employee learning and growth.
Module 1 33*
Lean Principles in the Organization
Lean concepts and tools;
! Lean a comprehensive system for decreasing waste and increasing cycle times and
quality
The tools of lean are 5S, velocity, spaghetti diagrams, level loading, and process
! 
cycle efficiency
The modern Lean approach was pioneered by Taiichi Ohno at Toyota during the 70's
! 
Goal is to identify processes that do not add value and eliminate them as much as
! 
possible
The concept of Value is from the customer's perspective
! 
In Lean, inventory is considered a drag, rather than an asset; so a lean business will
! 
do everything it can to minimize inventory
Module 1 34
Lean Principles - Value-Added and Non-Value-Added Activities
Value-Added vs. Non-Value-Added Activities;

! Value chain is a chain of activities that an organization performs in order to deliver a
valuable product or service to its customers

Value is defined by the customer, not by management
! 
A process is decomposed and each activity analyzed to see if it adds value or does
! 
not add value

Process is then improved and streamlined to reduce or eliminate non-value-added
! 
activities thus improving the value chain

Key tools concepts and methods for determining if an activity is value-added or non-
! 
value-added, then addressing the non-value-added activities include; Process Cycle

Efficiency, Value Stream Mapping, Spaghetti Diagrams, Kaizen, 5S, and Poke Yoke
Module 1 35
Lean Principles in the Organization
Lean philosophy encompasses three areas;
1. Transparency - easy access to useful information. An organization has achieved
transparency when processes can be observed and measured
2. Velocity – Also called Flow, it is the speed a process is completed. The ultimate
measure of velocity is the interval between when a customer places an order and the
delivery of the good or service they ordered. The ultimate goal of Lean is to increase
velocity in order to improve responsiveness to the customer.
3. Value - the set of qualities or characteristics for which a customer is willing to pay. It
is always assessed from the customer's perspective
Module 1 36
Lean Principles – Theory of Constraints
The Theory of constraints is an approach to improving processes by focusing on their
most problematic areas
!  These areas are known as constraints
!  Even the smoothest process has constraints
!  Improvement efforts are devoted to improving performance by removing or reducing
constraints without sacrificing quality elsewhere

!  Encourages businesses to improve continuously by diagnosing weaknesses and
addressing them
!  Exploiting the constraint is when an organization develops effective strategies for
maximizing the potential of the constrained area
Module 1 37
Value-Added vs. Non-Value-Added Activities;

The Japanese referred to non-value-added activities as Muda, which means waste
Examples of non-value added activities include;

!  Overproduction/overprocessing
!  Correction/rework
!  Excess inventory
!  Excess Motion
!  Transportation
!  Waiting
Module 1 38
Flow-Pull-Perfection
! Goal is to create continuous flow through the organization rather than improving
limited areas of a process

Pull means that each activity in a process should receive only the necessary
! 
materials and resources when a subsequent activity is 'demanding' the process be

completed
Perfection is defined as the ultimate goal of continuous improvement. By eliminating
! 
waste and streamlining processes, an organization can approach perfection
Module 1 39
Process Cycle Efficiency Metric;

Used to determine the most useful and positive ways to improve process cycle time (velocity or flow)
! 
Method for calculating process cycle efficiency is to divide value-added time by process lead time
! 
Little's law - process lead time is calculated by dividing the number of items in a process by the number
! 
of times the process is completed in an hour

While 100% would represent that all activities added value, it is more typical to approach 25%
! 
efficiency process cycle efficiency after the implementation of lean strategies; though on occasion
transactional processes can approach 50%
Module 1 40
Design for Six Sigma
1. Design for Six Sigma (DFSS)

1.  PDCA
2.  DMAIC
3.  Road maps for DFSS
4.  Basic failure mode and effects analysis (FMEA)
5.  Design FMEA and process FMEA
Module 1 41
Design for Six Sigma - PDCA
PDCA defines the improvement cycle that underpins the three key Six Sigma improvement
cycles, it stands for; Plan -> Do -> Check –> Act
It is an iterative process developed by Walter Shewhart and popularized by Deming.
Create a Plan,
! 
Do the plan (executes),

! 
Check the results,

! 
Act on the results by returning to the Plan phase in order to Plan whatever corrective
! 
action or improvement that should be pursued

Repeat as needed…
! 
Module 1 42
Improving Existing Processes
DMAIC
DMAIC is the Six Sigma Life Cycle for improving existing processes, it stands for;
Define - The purpose of this step is to clearly define the business problem, goals,
potential resources, project scope and establish a high-level project timeline
Measure - The purpose of this step is to objectively establish current baselines as the
basis for improvement. This is the data collection step.
Analyze - The purpose of this step is to analyze the collected data in order to identify
and validate the actual root cause of the quality or cycle time issues is
identified.
Improve - The purpose of this step is to identify, implement and test the solution(s) to
the root cause problem identified in the Analyze phase.
Control – The purpose of this step is to create and execute a control plan as well as
monitor the improvements to ensure continued and sustainable success
Module 1 43
Improving Existing Processes
DMAIC
DMAIC is best used when;
!  Only gradual improvements of existing processes and products are necessary
!  As well as to bring existing processes and products into alignment with customer
requirements and quality standards
!  It is the most common and the focus of the Greenbelt exam
Module 1 44
Design for Six Sigma (DFSS)
Road maps for DFSS
In this section we will;
Distinguish between DMADV (define, measure, analyze, design, verify) and IDOV
! 
(identify, design, optimize, verify)

Understand how DMADV and IDOV align with the DMAIC lifecycle
! 
Describe how DMADV and IDOV are used for improving the end product or process
! 
during the Design for Six Sigma (DFSS) phase
Module 1 45
Road maps for DFSS
DMADV is composed of the following steps;
Define – Define design goals that are consistent with customer demands and the
! 
enterprise strategy
Measure – Measure and identify CTQs (characteristics that are Critical To Quality),
! 
product capabilities, production process capability, and risks

Analyze – Analyze to develop and design alternatives
! 
Design – Design an improved alternative, best suited per analysis in the previous
! 
step
Verify – Verify the design, set up pilot runs, implement the production process and
! 
hand it over to the process owner(s)
Module 1 46
Road maps for DFSS
IDOV is the methodology most commonly associated with design for Six Sigma, or
DFSS. IDOV stands for;
Identification- Identify the customer needs, create an effective business model, and
! 
establish the Six Sigma team

Design - Use critical-to-quality metrics to design the processes
! 
Optimization - Adjust the factors that impact the process quality until the optimum
! 
outputs are achieved

Validation – Validate the new process and make any necessary adjustments
! 
Module 1 47
Road maps for DFSS
Both IDOV and DMADV have the same objectives and are rigorous in nature; their
only real difference is the terminology.
Overall goals are to reduce delivery time and development costs, as well as to
! 
increase effectiveness and better satisfy customers

Emphasizes defect prevention rather than reduction
! 
More concerned with the creation of new, high-quality processes than with the
! 
incremental improvement of old processes

Is best used for new product and process development because it includes a design
! 
phase
Also useful when the standard DMAIC lifecycle has proven ineffective at bringing an
! 
existing process up to sufficient quality standards as due to the process needing an

extensive overhaul
Module 1 48
Road maps for DFSS
To sum up which lifecycle to use
Use DFSS for 'greenfield' and for existing processes that require a substantial
! 
overhaul and redesign

Use DMAIC when incremental improvements to existing processes is all that is
! 
necessary
It is quite possible to start with DMAIC, realize that a substantive redesign is needed,
! 
then switch to using either IDOV or DMADV
Module 1 49
Basic failure mode and effects analysis (FMEA)
FMEA stands for Failure Mode and Effects Analysis
FMEA is used;
!  to evaluate a process or product to determine what might cause it to
fail and
!  As well as determine the effects that failure could have
Module 1 50
! FMEA provides an excellent basis for classifying and identifying
CTQs and other critical failure and effects variables
!  Objective of FMEA is to direct the available resources toward the
most promising opportunities

!  An extremely unlikely failure, even it has serious consequences, may
not be the best place to concentrate preventative efforts
!  Can be combined with decision analysis methods to help guide
preventive action planning
Module 1 51
The following steps are used in performing an FMEA:
1.  Define the system to be analyzed.
2.  Construct process maps
3. Conduct SIPOC (supplier, input, process, output, customer) analysis for each
subprocess in the system
4.  List the intended function of each step in the process or subprocess
5. For each process step, identify all potential item and interface failure modes and
define the effect on the immediate function or item, on the system, and on the mission
to be performed
6. Evaluate each failure mode in terms of the worst potential consequences which may
result and assign a severity classification category, or SEV
7. Determine the likelihood of occurrence of each failure mode and assign an
occurrence risk category, or OCC
Module 1 52
8. Identify failure detection methods and assign a detectability risk category, or DET
9. Calculate the risk priority number (RPN) for the current system. RPN = SEV X OCC
X DET
10. Determine compensating provisions for each failure mode
11. Identify corrective design or other actions required to eliminate failure or control the
risk
12. Identify effects of corrective actions on other system attributes
13. Document the analysis and summarize the problems which could not be corrected
and identify the special controls which are necessary to reduce failure risk
Module 1 53
FMEA severity, likelihood, detectability rating guidelines table
Rating Severity (SEV) Occurrence (OCC) Detectability (DET)
1 Customer won’t notice the effect Not likely Nearly certain to

or will consider it insignificant detect before reaching
the customer (p = 0)
2 Customer will notice Documented low failure Extremely low

the effect rate probability of reaching
the customer without detection
(0 <p <= 0.01)
3 Customer will become Undocumented low failure rate Low probability of

irritated at reduced reaching the customer
performance without detection (0.01 <p <=
0.05)
4 Customer Failures occur from time-to- Likely to be detected

dissatisfaction due to time before reaching the
reduced performance Customer (0.05 <p <=0.20)
5 Customer’s Documented moderate Might be detected

productivity is failure rate before reaching the
reduced Customer (0.20 <p ,=0.50)
Module 1 54
FMEA severity, likelihood, detectability rating guidelines table (Cont'd)
Rating Severity (SEV) Occurrence (OCC) Detectability (DET)
6 Customer will complain. Repair or Undocumented moderate Unlikely to be detected before

return likely. Increased internal costs failure rate reaching the customer (0.50 <p
(scrap, rework, etc.). <=0.70)
7 Reduced customer loyalty. Internal Documented high failure rate Highly unlikely to detect before
operations adversely impacted reaching the customer (0.70 <p
<=0.90)
8 Complete loss of customer goodwill. Undocumented high failure rate Poor chance of detection (0.90 <p
Internal operations <=0.95)
disrupted
9 Customer or employee safety Failures common Extremely poor chance of detection

compromised. Regulatory compliance (0.95 <p <=0.99)
questionable
10 Catastrophic. Customer or employee Failures nearly always occur Nearly certain that failure won’t be
endangered without detected ( p = 1)
warning. Violation of law or regulation
Module 1 55
Risk Priority Numbers;
A key to setting priorities; with larger RPNs having a higher priority
! 
Some organizations have set guidelines on what actions are to be taken based on the
! 
RPN value
The sum of the RPNs for all the potential failure modes is the overall RPN for the
! 
process in question
One can anticipate and compare the effects of proposed changes by calculating
! 
hypothetical RPNs for different scenarios

RPN is a measure for comparison within one given process only
! 
Relies heavily on engineering judgment

! 
Must be customized to fit the product or process that is being analyzed as well as the
! 
particular needs and priorities of the organization
Module 1 56
Design FMEA and Process FMEA
Design FMEA (DFMEA);
Is used to uncover design risk; including possible failure, degradation
! 
of performance and potential hazards

Typically the first FMEA tool used in product development
! 
The primary objective is to uncover potential failures associated with

! 
the product that could cause:

!  Product malfunctions
!  Shortened product life
!  Safety hazards while using the product
Design-FMEAs should be used throughout the design process from
! 
preliminary design until rollout into production
Module 1 57
Design FMEA and Process FMEA
Process Failure Mode and Effects Analysis (PFMEA);
Used when a new product or process is being introduced as well as for determining
! 
process controls
It can also play an important role in day to day improvement and problem solving
! 
!  Used to uncover potential failures that can:

!  Impact product quality
!  Reduce process reliability
!  Cause customer dissatisfaction
!  Create safety or environmental hazards
Ideally should be conducted prior to start-up of a new process, but can also be
! 
conducted on existing processes
Module 1 58
End of Module 1
1.  Six Sigma and Organizational Goals
1.  Value of Six Sigma
2.  Organizational Goals and Six Sigma Projects
3.  Organizational Drivers and Metrics
2.  Lean Principles in the Organization

1.  Lean concepts
2.  Value-added and non-value-added activities
3.  Design for Six Sigma (DFSS)

1.  Road map for DFSS
2.  Basic failure mode and effects analysis (FMEA)
3.  Design FMEA and Process FMEA
Module 1 59
Module 2 – Define Phase – Project Identification
Module 2 – Define Phase – Project
Identification
Outline
1. Overview of Define Phase
2. Project selection
3. Process elements
4. Benchmarking
5. Process inputs and outputs
6. Owners and stakeholders
Module 2 61
Overview of Define Phase
!  The Define phase focuses on identifying and articulating a project’s

important characteristics, including identification of the goals, objectives,
and scope of the project
!  The team members and sponsors are identified, as well as the proposed
schedule for the project
!  The desired result of the project is defined
!  The team also identifies the stakeholders, the input/output structure, and
the functions involved.
Module 2 62
Project Selection
Three reasons to take on a project;

1. Make Money
2. Save Money
3. Because the government told us to
Module 2 63
Module 2 –Define Phase – Project Identification
Project Selection
For the first two reasons, there are three ways to decide on a
specific project;
1. An 'in your face' problem or opportunity
2. Brainstorming based on individual or organization knowledge
of possible areas for improvement or opportunities to pursue
3. Structure project selection approach based on data impacting
the bottom line metrics.
Module 2 64
Project Selection
Project Selection Process Deliverables;

Business Case – The Business Case is a high level description of the area of
concern. It answers two primary questions; what is the business rational for
considering the project and, what is our proposed focus for the improvement effort?
Project Charter – The Project Charter is a more detailed version of the Business
Case. It further focuses the improvement effort. It has two primary sections; basic
project information and, simple project performance metrics.
Cost Benefits Analysis (CBA) – The CBA is a comprehensive financial evaluation of

the project. It is concerned with the detail of the benefits in regard to cost &
revenue impact that is expected to be realized as a result of the project
Module 2 65
Project Selection
Responsible Frequency
Party Resources of Update
Champion/
Business Business Unit
Executive Sponsor N/A
Case Members
Project Black or Green Champion &

Ongoing
Charter Belt(s) Master Black Belt
Cost
Business Champion & Ongoing /
Benefits
Unit Financial Rep Black or Green Belt(s) D,M,A,I,C
Analysis
Module 2 66
Project Selection
The problem or opportunity to be addressed is identified by the Champion or Process

Owner with the Business Case is the output. Once its identified, the appropriate
metrics or Key Performance Indicators (KPIs) are selected. Examples would be;
!  EBIT
!  Cycle time
!  Defects
!  Cost
!  Revenue
!  Complaints
!  Compliance
!  Safety
Module 2 67
Project Selection
Selecting a Key Business Measure or Key Performance Indicator (KPI);

Only focus on one key business measure or KPI
! 
The selected measure or KPI should tie in directly with the organization's strategic
! 
objective
Narrow in on the greatest opportunity for improvement
! 
Determine how success will be measured

! 
Break down to an actionable level of detail

! 
Module 2 68
Project Selection
Several key Business Measures, Metrics, or KPIs fall into the following
overall categories;
!  Critical-to-cost
!  Critical-to-schedule
!  Critical-to-quality
Module 2 69
Project Selection
Critical-to-cost;
Identifies areas of a process that significantly increase the expense
! 
Critical-to-cost metrics should include not only the typical cost of a task, but
! 
also the increased cost of errors incurred in the performance of this task
The amount of money required to align a product or service with quality
! 
baselines is known as the cost of quality
Module 2 70
Project Selection
Critical-to-schedule;
Cycle time is the most common critical-to-schedule metric. Cycle time is the
! 
duration required for the completion of a defined process

Improvement of critical-to-schedule issues begins with distinguishing
! 
between process steps that add value and process steps that do not add
value
Use process efficiency and velocity numbers to assess value added relative
! 
to cycle time
Module 2 71
Project Selection
Critical-to-schedule (Cont'd);
In most Six Sigma projects, cycle time is considered secondary to metrics
! 
related to quality or cost.

Focusing exclusively on reducing cycle time is likely to compromise quality
! 
It can be useful to baseline quality and cost metrics and then work to reduce
! 
cycle time
Module 2 72
Project Selection
Critical-to-quality;
A common critical-to-quality metrics is yield, or the amount of completed
! 
product divided by the amount of product that began the process

The difference between perfection and reality is known as the scrap rate
! 
While useful, it does not indicate where in the process errors occurred
! 
Yield does not distinguish those pieces of scrap that can still be salvaged
! 
Yield is noted as a decimal, where 1 would equal 100%

! 
See Module 6 for several more andvanced yield metrics

! 
Module 2 73
Project Selection
Key KPI → Detailed Metric → Activity → Process

→ Detailed Metric → Activity → Process
1. An Activity is an action that has one or more processes associated to it;
such as a customer call received at a call center
2. A process is a specific, repetitive, and systematic set of steps to be followed
to produce a specific value-added outcome; such as signing up a new
customer for cable service. Processes have inputs, processing steps, and
outputs
Module 2 74
Project Selection
The Business Case communicates the need for the project in terms of
meeting business objectives
It is comprised of:
!  Output unit (product or service) for external or internal customer
!  Key business measure or KPI of output unit
!  Baseline performance of key business measure or KPI
Gap in baseline performance of key business measure or KPI from business
! 
objective
Module 2 75
Project Selection
There are various approaches to selecting a project that we have already
touched on. Even if you started with an 'in your face' or brainstorming project
selection process, it is highly recommended that you validate the selection
using a structured approach.
Module 2 76
Project Selection
The structured approach.uses tools and data such as;
Customer Feedback/Complaint Data
! 
Line Graph
! 
Run Charts
! 
Control Charts
! 
Process Flowcharting
! 
Layout Diagramming
! 
Process Watch
! 
Voice of Customer – Interviewing

! 
Stratification using Bar, Pie, Radar Charts, Pareto Analysis

! 
Module 2 77
Project Selection
Establishing the Primary Metric:
!  The Primary Metric is a quantified measure of the defect or primary issue
!  Links to the KPI or Key Business Measure
We can have only One Primary Metric. Recall the equation Y = f (X); well
! 
once your defect is located then Y will be your defect. Your primary metric will
measure it
!  Serves as the indicator of project success
Module 2 78
Project Selection
Establishing Secondary Metrics:
Secondary Metrics measure potential changes that may occur as a result of
! 
changes in the Primary Metric

Measures positive & negative consequences resulting from changes in the
! 
process
!  Can have multiple Secondary Metrics
Module 2 79
Project Selection
Cost Benefit Analysis;
Benefits should be calculated on the baseline key business process performance
! 
relating to a business measure or KPI(s)

The Project Measure (Primary Metric) has to directly link between the process and its
! 
KPI s
Goals have to be defined realistically
! 
Benefits should be annualized

! 
Benefits should be measured in accordance with Generally Accepted Accounting

! 
Principles (GAAP)
Module 2 80
Project Selection
Generating Charts;
!  Display Primary and Secondary Metrics over time
!  Should be updated regularly throughout the life of the project
!  One for Primary Metric and one for each of the Secondary Metrics
!  Typically utilize Time Series Plots
Module 2 81*
Process Elements
Six Sigma has a process focus In order ;
To understand how and why work gets done
! 
To identify and deconstruct customer & supplier relationships

! 
To manage for maximum customer satisfaction while utilizing minimum resources

! 
To analyze and measure the process from start to finish as it is currently being
! 
performed
Resolve defects and errors by focusing on the process, not the people
! 
Module 2 82
Process Elements
Process Maps
!  Identify the complexity of the process
!  Communicate the steps in the process
!  Represents what is actually happening, not what you think is happening
!  Should be created by the people who are closest to the process
Module 2 83
Process Elements
Process Maps
In the Define phase, they are used to record top-level processes
! 
In the Measure phase, they are used to record the lower process levels and reveal
! 
differences in the perceptions of shareholders

In the Analyze phase, process maps are used to investigate the sources of variation
! 
or excessive cycle time

In the Control phase process maps may be used to record process adjustments
! 
Module 2 84
Process Elements
By mapping processes we can identify important characteristics;
1. Process inputs (X’s)
2. Supplier requirements
3. Process outputs (Y’s)
4. Actual customer needs
5. All value-added and non-value added process tasks and steps
Module 2 85
Process Elements
By mapping processes we can identify important characteristics;
6.Data collection points
!  Cycle times
!  Defects
!  Inventory levels
!  Cost of poor quality, etc.
7.Decision points
8.Problems that have immediate fixes
9.Process control needs
Module 2 86
Process Elements
Standard symbols for Process Mapping;
RECTANGLE indicates a step. PARALLELAGRAM shows

Statements should begin input or output data
with a verb
DIAMOND indicates a decision ELLIPSE shows the start

point. Only two paths emerge and end of the process
from a decision point: No and Yes
ARROW shows the CIRCLE WITH A LETTER OR

1 NUMBER INSIDE symbolizes
connection and direction
the continuation of a
of flow
flowchart to another page
Module 2 87
Process Elements
One of the Define Phase deliverables is the high level Process Map; which as a
minimum must include;
!  Start and stop points
!  All process steps
!  All decision points
!  Directional flow
!  Value categories
This will be fleshed out in the Measure Phase
Module 2 88
Process Elements
Process Maps come in two forms;
Linear Flow
Calls
Customer Take Make Cook Pizza Box Deliver Customer
for
Hungry Order Pizza Pizza Correct Pizza Pizza Eats
Order
This diagram shows the process steps in a sequential flow, generally ordered from
an upper left corner of the map towards the right side
Module 2 89
Process Elements
Deployment Flow or Swim Lane
Customer
Customer Calls for Customer

Hungry Order Eats
Cashier
Take
Order
Pizza Box
Cook
Make Cook
Pizza Pizza Correct Pizza
Deliverer
Deliver
Pizza
The Swim Lane map shows who or which department is responsible for the steps
in a process. A timeline can be added to show how long it takes each group to
perform their work.
Module 2 90
Process Elements
Value categories are;
Value Added:
!  Physically transforms the thing going through the process
!  Adds quality or value
!  Important from the customer s perspective
Value Enabling:
!  Satisfies the requirements of non-paying external stakeholders, such as
regulators
Non-Value Added
!  Everything else
Module 2 91
Process Elements
The relationship from one process to the next in an organization creates a

! 
Value Chain of suppliers and receivers of process outputs.

Each process has a contribution and accountability to the next to satisfy the
! 
external customer.
External customers needs and requirements are best met when all process
! 
owners work cooperatively in the Value Chain.
Module 2 92
92
Process Elements
There three views of a process;
1. What is documented
2. What is actually is
3. What it should be
Module 2 93
Process Elements
The No Process Problem;
Many businesses and industries are notorious for their lack of “process-thinking.”
! 
You may discover that there is no process for performing the work.
! 
In these cases, bypass the Analysis step and proceed directly to Improve to design
! 
and implement a production process that meets the needs of the customers
Key question is “Why was there no process, and what other products and services
! 
are being ‘produced’ without a process?
Initially develop and implement the “best” process you can

! 
Then bring the people who work the process together to develop the best method
! 
Module 2 94
Process Elements
Process Exists, but not Followed. Either;
1. A “good” process exists (one that can “produce” the product/service at the required
quality levels), but it is not being followed.
Two questions come to mind:
1.  Does staff understand the importance of the “standards?”
2.  Does management emphasize their importance?
Solution is education and communication
Module 2 95
Process Elements
Or;
2. A “bad” process exists. Of course, the process must be revised
But the questions must be asked
1.  Why are processes difficult to follow?
2.  Are suggestions for improvement not offered, or taken?
3.  Are the ad hoc 'processes' better?
Module 2 96
Process Elements
Process Boundaries and Interfaces;
!  Process Boundary defines the process entry and exit points where inputs flow in and
outputs flow out
!  Provides a clear picture of the process scope
!  Defines the external interfaces
!  Internal interfaces
!  Hand-off points within the process boundaries
!  Most critical where the process crosses functional or organizational
borders
!  Most process inefficiencies are related to insufficient interface communication (lack
of coordination)
!  Important to identify critical interfaces early on
Module 2 97
Benchmarking
Benchmarking;
!  Is a process for obtaining a measure
!  Comes in three types; competitive, collaborative and best practices
!  Used to measure progress against
!  Dimensions typically measured are quality, time and cost
Module 2 98
Benchmarking
Benchmarking process;
1. Determine what and why you’re benchmarking - Decide on the real reasons
you’re benchmarking. Identify what you want to benchmark and the reasons why
2. Identify the drivers – find the drivers that will be used to determine the particular
metric you are benchmarking.
3. Find a way to measure – how are you going to measure these driver?
4. State your current situation – here you need to find your base point – measure
your current performance.
5. Identify who or what you are going to benchmark against – who do you want to
compare against? Competitors? Best Practices?

Module 2 99
Benchmarking
Competitive Benchmarking;
Can be defined as the continuous process of comparing a firm’s practices
! 
and performance measures with that of its most successful competitors

Select the best-in-class companies for each area to be benchmarked
! 
Measure the performance of the best-in-class companies for each

! 
benchmark being considered

Compare and use the comparison as input to your project selection process
! 
Module 2 100
Benchmarking
Collaborative Benchmarking;
Carried out collaboratively by groups of companies; either related
! 
subsidiaries or otherwise independent companies collaborating

Easiest when the collaborating organizations are not in a highly competitive
! 
industry; such as education or healthcare

Still possible in more competitive industries.
! 
Use standard benchmarking process

! 
Module 2 101
Benchmarking
Best Practices Benchmarking;
Is used to identifying and analyze world-class performance. This form of
! 
benchmarking is used most when a company needs to go outside of its own

industry
The rational is that customer satisfaction is driven by critical-to-quality
! 
measures that are similar regardless of the industry

Challenge is to both identify the best-of-breed company and to deconstruct
! 
its processes
Module 2 102
Benchmarking
There is a wealth of benchmarking information already gathered and
available. Some available sources are;
1. American Productivity & Quality Center (APQC)
2. APQC Knowledge Sharing Network
3. The Benchmarking Exchange
4. Best Practices, LLC & Global Benchmarking Council
Module 2 103
Process Inputs and Outputs
The Supplier, Inputs, Process, Output, Customer (SIPOC) model;
Provides a comprehensive look at a process.
! 
SIPOC is used during the define stage of DMAIC to identify each top-level process,
! 
as well as its stakeholders

SIPOC is initiated with the creation of a flowchart or process map
! 
Typically, the first category to be identified is the outputs.

! 
Module 2 104
SIPOC;
!  The list of Customers from your SIPOC are the starting point for the Voice of the
Customer analysis
!  The major process steps (macro map) from your SIPOC are the overview for later
detailed process mapping
!  The Inputs, Process Steps, and Outputs on your SIPOC generates ideas for what
can and should be measured, which feeds the Data Collection Plan in the Measure
phase
!  The SIPOC contains clues about potential root causes that drive performance
Module 2 105
SIPOC;
Suppliers are those persons who contribute inputs to the process
! 
Inputs are defined as all of the knowledge, resources, and information required to
! 
produce the desired output

Process is defined as any task that translates inputs into outputs
! 
Outputs are the deliverables, or the products of the process

! 
Customers are all of those parties that receive the deliverables (outputs)
! 
Module 2 106
Module 2 107
107
SIPOC Map Construction
1. Name the process
2. Clarify the start and the stop (boundaries) of the process
3. List key outputs and customers
4. List key inputs and suppliers
5. Identify, name, and order the major process steps (guideline: 5 – 7 maximum)
Module 2 108
Owners and Stakeholders
There is a wide range of Owners and Stakeholders;
Senior Executive
Provides the impetus, direction & alignment necessary for Six Sigma ultimate
! 
success
The Senior Executive should:
! 
!  Study Six Sigma management

!  Link company’s objectives to Six Sigma projects
!  Champion Six Sigma projects
!  Constantly review Six Sigma projects progress
Module 2 109
Executive Committee Member
!  They are the top management of an organization
!  Executive Committee Members should:
!  Deploy Six Sigma throughout the organization
!  Prioritize and manage Six Sigma portfolio
!  Assign champion, BB and GB to Six Sigma projects
!  Remove barriers to Six Sigma management
!  Provide resources for Six Sigma management
Module 2 110
Process Owner
! Is the manager of a process. The process owner should be identified and involved in
all Six Sigma projects relating to the process owner area.

A process owner should:
! 
!  Empower employees to follow and improve best practice methods

!  Accept and manage the improved process after completion of the Six
Sigma project
!  Understand how the process works, the capability of the process, and
the relationship of the process to other processes in the organization
Module 2 111
Customer
! Is the recipient of the output (good, service, product or idea) obtained from a process
! Can be internal or external
! Has the final 'say' on what constitutes acceptable quality and value; especially the
external customer
! Classic Lean definition of value is anything the customer is willing to pay for
! Concept of Voice of the Customer is key to Six Sigma
Other Stakeholders – Regulators, suppliers, team members, employees, etc.
Module 2 112
End of Project Identification
!  Define Phase Overview

!  Project selection
!  Process elements
!  Benchmarking
!  Process inputs and outputs
!  Owners and stakeholders
Module 2 113
Module 3 – Define Phase – Voice of the Customer
Module 3 – Define Phase –
Voice of the Customer
Outline
1. What is the Voice of the Customer
2. Voice of the Customer Process
3. Customer identification
4. Customer data
5. Customer requirements
Module 3 115
What Is the Voice of the Customer?
!  The term Voice of the Customer (VOC) is used to
describe customers’ needs in a process improvement
effort and their perceptions of your product or service.
Module 3 116
Using the Voice of the Customer
!  Understand why the Voice of the Customer (VOC) is
critical
!  Know how to create a plan for gathering VOC data
!  Know both reactive and proactive ways to gather VOC
information
!  Know how to analyze data through the use of affinity
diagrams and Kano diagrams

!  Be able to use a CTQ tree diagram to identify customer
requirements and set specifications for them
Module 3 117
!  VOC data helps an organization and a project to:
!  Decide what products and services to offer
!  Identify critical features and specifications for those products,
process outputs and services

!  Decide where to focus improvement efforts
!  Get a baseline measure of customer satisfaction to measure
improvement against
!  Identify key drivers of customer satisfaction
Module 3 118
Why Collect VOC Data
!  Customer requirements change constantly
!  Specifications tend to focus on technical data only
!  Critical to Quality (CTQ s) are measures that we use to capture VOC
properly. (also referred to in some literature as CTC s – Critical to
Customer)
!  CTQ s can be vague and difficult to define
Module 3 119
VOC Process
!  Outcomes
!  A list of customers and customer segments
!  Identification of relevant reactive and proactive sources
of data
!  Verbal or numerical data that identify customer needs
!  Defined Critical to Quality requirements (CTQ)
!  Specifications for each CTQ
Based on Rath & Strong
Module 3 120
Customer identification
!  Goal
!  Identify your customers
!  Decide what you need to know about their needs
!  Decide when and how you will get this information
Module 3 121
S C
U U
P S
P T
L Inputs Process Outputs O
I AB-588.2 M
E E
R R
S S
!  What are the outputs of your process? Who are the customers of that
output?
!  Are there particular groups of customers whose needs are especially
important to your organization and project success?
Module 3 122
S C
U U
P S
P T
L Inputs Process Outputs O
I AB-588.2 M
E E
R R
S S
!  What are the outputs of your process? Who are the customers of that
output?
!  Are there particular groups of customers whose needs are especially
important to your organization and project success?
Module 3 123
Customer Identification
!  Customer status: Former Customers, Current Customers, Customers of
Competitors, Substitute Customers
!  Where they are in the “customer chain”
!  Internal user
!  Distributor
!  End user
!  Geography
!  Industry, Division or Department
!  Demographics
Module 3 124
Customer Identification
!  If your customers seem to have similar needs across the board, you
don’t need to divide them into segments
!  If you suspect that different groups will have significantly different

needs, and that these differences will influence how you structure
your process, product, or service, then you need to think in terms of
segments
Module 3 125
Customer Data
!  Revisit your charter—what is the purpose of your project?
!  How does your purpose relate to customer needs?
!  What do you need to know about the needs of the customers you’ve
identified to make sure your project’s purpose stays on track?
Module 3 126
Customer Data
For all customers, you should ask questions such as:
1. What is important to you about our process/product/service? (Ask them to rank
each of these needs in order of importance.)
2. What do you think of as a defect?
3. How are we performing on the areas you consider important?
4. What do you like about our product/service?
5. What can we improve about our process/product/service?
What can we do to make your job easier?
6. What specific recommendations would you make to us?
Module 3 127
Customer Data
!  Reactive Data Collection - Data comes in whether action is taken or not
!  Reactive collection generally gather data on:
!  Current and former customer issues or problems as
communicated by them
!  Current and former customers’ expressed interest in particular
products, process outputs or services as communicated by them

!  Proactive Data Collection – Requires action in order to gather data
Module 3 128
Customer Data
Typical Reactive Data
!  Customer complaints
!  Problem or service hot lines
!  Technical support calls
!  Customer service calls
!  Claims, credits, contested payments
!  Sales reporting
!  Product return information
!  Warranty claims
!  Web page activity
Module 3 129
Customer Data
Typical Proactive Data
!  Interviews
!  Focus groups
!  Surveys
!  Comment cards
!  Data gathering during sales visits or calls
!  Direct customer observation
!  Market research, market monitoring
!  Benchmarking
!  Quality scorecards
Module 3 130
Customer Data
The last steps in planning your data collection are to decide;
!  Specifically how the data will obtained
!  Over what time frame the data gathering should take place
!  And how will the data be recorded
Module 3 131
Customer Requirements
!  Goal is to generate a list of key customer needs in their language
!  Summarize the data in a meaningful way
Module 3 132
Voice of the Customer- Customer Requirements
Quality Function Deployment (QFD)
Is a process for translating customer requirements into appropriate company
requirements at each stage from research and product development to
engineering and manufacturing to marketing/sales and distribution
Understanding the VOC is key to successful QFD!!!
Module 3 133
QFD was developed in Japan in the late 1960s by Professors Yoji Akao and
Shigeru Mizuno.
They aimed at developing a quality assurance method that would design
customer satisfaction into a product before it was manufactured. Prior quality
control methods like Ishikawa were primarily aimed at fixing a problem during or
after manufacturing.
Module 3 134
QFD's Key Rationale:
1 Customers are our number one concern. Satisfied customers keep us
in business. Therefore, we must have an excellent understanding of
their needs.
2 Proactive product development is better than reactive product
development. QFD can help a company move toward a more proactive
approach.
3 Quality is a responsibility of everyone in the organization. QFD is a
team methodology which encourages a broader employee involvement
and focus.
4 The QFD methodology helps an organization determine the most
effective applications for many engineering and analytical tools such as:
Design of Experiments, Failure Analysis and Statistical Process Control.
Module 3 135
QFD's Recognizes:
1.The Impact of Needs on the Customer
2.That Customer Needs Change With Time
3.The impact of Communication of Customer Wants Throughout the
organization
Module 3 136
Where does QFD fit?
Quality Improvement Tools

QFD •  Taguchi Methods
•  FMEA’s • Statisical Process
- Planning Tool
•  Fault Tree Analysis Control (SPC)
- Customer Driven •  Cause-Effect Diagram
•  Pareto
- Proactive
•  Benchmarking
• Check Sheets
- Cross Functional Teams •  Pugh Concept Selection - Monitor
•  Etc
- Continuous Improvement
- Hold the “Gains”
Module 3 137
QFD Flow
Customer Requirements
Converted to
Company Measures
Converted to
Part Characteristics (Design)
Converted to
Manufacturing Process
Converted to
Production Requirements
(Day to Day Operations)
Module 3 138
When should QFD be used?
1 Customers are complaining or aren’t
satisfied with your product or service.
2 Market share has been consistently
declining.
3 Extended development time due to
excessive redesign, problem solving, or fire
fighting.
4 Lack of a true customer focus in your
product development process.
5 Poor communications between
departments or functions.
(Over-the -wall product development).
6 Lack of efficient and/or effective teamwork.
Module 3 139
When should QFD be used?
1. Complex Product Development Initiatives
1. Communications Flow Down Difficult
2. Expectations Get Lost
2. New Product Initiatives / Inventions
1. Lack of Structure or Logic to the
Allocation of Development Resources.
3. Large Complex or Global Teams
1. Lack of Efficient And/or Effective
Processes
2. Teamwork Issues
4. Extended Product Development Times
1. Excessive Redesign
2. Changing Team
3. Problem Solving, or Fire Fighting.
Module 3 140
Competitive Advantages from QFD;
! Fewer and Earlier Changes
! Shorter Development Time
! Fewer Start-up Problems
! Lower Start-up Cost
! Warranty Reduction
! Knowledge Transfer
Customer Satisfaction
! 
Module 3 141
KANO MODEL CUSTOMER
SATISFACTION
(Of Quality/Features) EXCITEMENT
VERY SATISFIED
• UNEXPECTED, PLEASANT
SURPRISES
• 3M CALLS THEM
CUSTOMER DELIGHTS
UNSPOKEN
DID NOT
DO AT ALL SPOKEN DEGREE OF
AGREEMENT
PERFORMANCE
• ONE-DIMENSIONAL FULLY
• MOST MARKET BASIC ACHIEVED
RESEARCH
UNSPOKEN • EXPECTED
• TYPICAL OF
‘INVISIBLE’ PRODUCTS
VERY DISSATISFIED
TIME
Module 3 142
Voice of Translating
the customer for action
WHAT WHAT HOW
The items contained in this list are

usually very general, vague and
difficult to implement directly - they
require further detailed definition.
One such item might be good ride
which has a wide variety of meanings
to different people.
This is a highly desirable product
feature, but is not directly actionable.
Module 3 143
COMPLEX UNTANGLING
RELATIONSHIPS THE WEB WITH A MATRIX
HOW
WHAT HOW
WHAT
RELATIONSHIPS
Module 3 144
House of Quality is a
complex matrix diagram
extensively used in QFD
Interrelationships
Customer
importance
ratings
How to satisfy
customer wants
assessment
Competitive
What the Relationship
customer matrix
wants
Target values Weighted

rating
Technical
evaluation
Module 3 145
House of Quality; Interrelationships
How to Satisfy
What the Customer Wants
customer
Analysis of
Competitor
What the
Customer Relationship
s
wants Wants
Matrix
Technical
Attributes and
Evaluation
Lightweight 3 Customer
importance
Easy to use 4 rating
Reliable 5 (5 = highest)
Easy to hold steady 2
Color correction 1
Module 3 146
House of Quality;
Interrelationships
Low electricity requirements
How to Satisfy
Customer Wants
Analysis of
Competitor
What the
s
Matrix
Wants
Aluminum components
Technical
Attributes and
Evaluation
Ergonomic design
Auto exposure
How to Satisfy
Paint pallet
Customer Wants
Auto focus
Module 3 147
House of Quality; Interrelationships
How to Satisfy
Customer Wants
High relationship
Analysis of
Competitor
What the
s
Matrix
Wants
Medium relationship Technical

Attributes and
Low relationship Evaluation
Lightweight 3
Easy to use 4
Reliable 5
Color corrections 1
Relationship matrix
Module 3 148
House of Quality;
Interrelationships
How to Satisfy
Customer Wants
Analysis of
Competitor
What the
s
Relationships between Wants
Matrix
Aluminum components
the things we can do Technical

Attributes and
Evaluation
Ergonomic design
Auto exposure
Low electricity
requirements
Paint pallet
Auto focus
Module 3 149
Interrelationships
How to Satisfy
Customer Wants
Analysis of
Competitor
What the
House of Quality; Customer Relationship
s
Matrix
Wants
Technical
Attributes and
Evaluation
Lightweight 3
Easy to use 4
Reliable 5
Color corrections 1
Our importance ratings 22 9 27 27 32 25
Weighted rating
Module 3 150
Interrelationships
How to Satisfy
House of Quality; Customer Wants
Company B
Company A
Analysis of
Competitor
What the
s
Matrix
Wants
Technical
Attributes and
Evaluation
How well do competing

products meet customer wants
Lightweight 3 G P
Easy to use 4 G P
Reliable 5 F G
Easy to hold steady 2 G P
Color corrections 1 P P
Our importance ratings 22 5
Module 3 151
House of Quality;
Interrelationships
How to
Satisfy
Failure 1 per 10,000

Customer
Analysi
Compe
titors
What Wants
s of
Relationship
the Matrix
Custo
mer
Panel ranking
Wants Technical
Attributes Target values
and
Evaluation (Technical
2 circuits
attributes)
2’ to ∞
0.5 A
75%
Company A 0.7 60% yes 1 ok G

Technical Company B 0.6 50% yes 2 ok F
evaluation
Us 0.5 75% yes 2 ok G
Module 3 152
Voice of the Customer- Customer
Low electricity requirements

Requirements
Aluminum components
Ergonomic design
Auto exposure
Company B
Company A
Paint pallet
Auto focus
Completed House of Quality Lightweight 3 G P
Easy to use 4 G P
Reliable 5 F G
Easy to hold steady 2 G P
Color correction 1 P P
22 9 27 27 32 25
Our importance ratings
Failure 1 per 10,000

Panel ranking
Target values
(Technical
attributes) 2 circuits
2’ to ∞
0.5 A
75%
Company A 0.7 60% yes 1 ok G

Technical
evaluation Company B 0.6 50% yes 2 ok F
Module 3 Us
153
0.5 75% yes 2 ok G
House of Quality - What to look for
!  Blank rows - Unfulfilled customer wants
!  Blank columns - Unnecessary requirements. Incomplete customer
wants
!  Rows or columns with only weak relationships - Banking a lot on
“maybe’s”
!  Unmeasurable “HOWs” - Difficult to do what can’t be measured
!  Too many relationships - More than 50% relationships make it hard
to prioritize
!  Opportunities to excel
!  Negative correlations -Try to eliminate. Trade off if needed
!  Conflicting competitive assessments
Module 3 154
House of Quality – Things to ask
•  How was the voice of the customer determined?
•  How were the design requirements (etc) determined? Challenge the usual in-
house standards.
•  How do we compare to our competition?
•  What opportunities can we identify to gain a competitive edge?
•  What further information do we need? How can we get it?
•  How can we proceed with what we have?
•  What trade-off decisions are needed?
Module 3 155
House of Quality – Things to remember
•  The process may look simple, but requires effort.

•  Many of the entries look obvious - after they are written down.
•  If there aren’t some “tough spots” the first time, it probably isn’t being done
right!
•  Focus on the end-user customer.
•  Charts are not the objective.
•  Charts are the means of achieving the objective.
•  Find reasons to succeed, not excuses for failure.
Module 3 156
QFD - Traps
!  QFD on everything
!  Inadequate priorities
!  Lack of teamwork
!  Wrong participants
!  Turf issues
!  Lack of team skills
!  Lack of support
!  Too much “chart focus”
!  Handling trade-offs
!  Too much internal focus
!  “Stuck on tradition”
!  “Hurry up and get done”
!  Failure to integrate QFD
Module 3 157
End of Voice of the Customer
What is the Voice of the Customer

! 
Voice of the Customer Process

! 
! 
Customer data
! 
Customer requirements
! 
Module 3 158
Module 4 – Define Phase – Project Management Basics
Project Management Basics
Outline
1. Project charter
2. Project scope
3. Project metrics
4. Project planning tools
5. Project documentation
6. Project risk analysis
7. Project closure
Module 4 160
Project Management Basics – Project Charter
A project charter is the initiating document for the project. It is used to:
•  Better define your project
•  Define what is Critical to Quality (CTQ’s) to the Customer
•  Write a business case (links project to business goals)
•  Write a problem and goal statement
•  Scope a project
–  State the problem or opportunity
–  Establish the project goal(s)
–  Identify criteria for success
–  List assumptions, risks and obstacles
–  Communicate the above
–  Obtain management support
Module 4 161
The Project Charter expands on the Business Case by clarifying the project
focus and performance measures. It is composed of;
Problem Statement – What is the defect or error in the process; and what are the
! 
consequences
! Objective Statement – What is the target process improvement
! Scope – Articulates the boundaries of the project
! Primary Metric – The actual measurement of the defect or error in the process
! Secondary Metric(s) – Measures of potential consequences (+ / -) as a result of
changes in the process

! Charts – Of the Primary and Secondary Metrics over a period of time
! Standard Project Information – Key stakeholders, start & end dates, etc.
Module 4 162
A good Project Charter;
Will establish clear deliverables, so its success or failure can be measured
! 
Will direct employee efforts to the right areas because it will identify the key
! 
variables that affect performance at all levels

Will ensure that a proposed project does not interfere with other work
! 
performed in the company

Will ensure that the planned efforts are directed to the most important
! 
aspects of performance
Is a living document. Expect to revise it during the Measure phase
! 
Module 4 163
Problem Statement
!  A problem is the unsatisfactory result of a job or process

!  So what? What is the impact on the ‘customer’?
!  What problem or gap are you addressing?

!  What impact will closing the gap have on the customer?
!  How will you know things are better?

!  It should not include theories about solutions
Module 4 164
Problem Statement
Remember the 5W’s +1H
!  What are the symptoms? What happens when the problem appears?
!  Where do symptoms appear? Where don’t they appear?
!  When do symptoms appear? Where don’t they appear?
!  Who is involved? Who isn’t?
!  Why deal with it now?
!  How do we think it happened? How widespread is the problem?
Module 4 165
Problem Statements
!  A poor problem statement
–  Product returns are too high and will be reduced by analysing first
and second level Pareto charts
!  A better problem statement

–  Product returns are 5% of sales resulting in a business unit negative
profit impact of $5M and reduced market share of 10%
Module 4 166
For any process, variation is the main reason for poor
performance, as it is;

For any process, variation is the main reason for poor performance, as it is;
•  The enemy of certainty
•  The enemy of customer satisfaction
•  Drives the unknown
•  Adds to customer (and employee) disbelief
•  Adds to lack of confidence in the ability of processes
•  Increases risk that a result will not meet expectations
•  Variation is a driver of defects
So the problem statement will very often point us a uncovering the reason for
variation
Module 4 167
Project Objectives
!  Should address the problem statement
!  Quantify performance improvement
!  Should also identify timing
!  Needs to be Measurable, Actionable and Realistic
!  Quality / Quantity / Time / Cost
!  A poor objective
!  Reduce product returns by implementing performance measures and
objectives
!  A better objective
!  Reduce product returns of product line abc from 5% to 2.5% by the
year end, to reduce overall returns by 1% and saving $1M

Module 4 168
Project Management Basics – Project Scope
Project Scope
!  A project charter will include a clear description of the project scope

!  For a number of reasons, it is better for projects to have a limited scope
!  In general, Six Sigma projects should take no more than four months
!  For setting scope, ask “what represents a significant improvement?”
!  For example; X amount of an increase in yield or X amount of defect
reduction
!  Use Framing Tools to establish the initial scope; such as process maps,
Pareto charts, and other quality tools
Module 4 169
!  A process map is a graphical representation of the flow of a process
!  A detailed process map includes information that can be used to improve the
process, such as:
!  Process Times
!  Quality
!  Costs
!  Inputs
!  Outputs
Module 4 170
Types of Process Map

!  Basic process map
!  Detailed process map
!  Work-flow (spaghetti diagrams)
!  Top-down flowchart
!  Deployment flowchart
!  Opportunity flowchart
!  Current State / Future state maps
Module 4 171
Process Maps are used to;
!  Identify areas for focus of improvement efforts
!  Identify and eliminate non-value added steps
!  Combine operations
!  Assist root cause analysis
!  Baseline for failure mode and effect analysis (FMEA)
!  Identify potential controllable parameters for designed experiments
!  Determine needed data collection points
!  Eliminate unnecessary data collection steps
Module 4 172
Process Map Example
Module 4 173
Process Maps
!  Should include
!  Major activities and tasks
!  Sub-processes
!  Process boundaries
!  Inputs
!  Outputs
!  Documents reality, not how you think the process is supposed to be

completed
!  Should identify opportunities for improvement
Module 4 174
Steps for Process Mapping
!  Scope the process
!  Identify the start and end points of the process of interest
!  Document the top level process steps

!  Create a flow chart
!  Identify the inputs and outputs

!  What are the results of doing each process step? (Y’s)
!  What impacts the quality of each Y? (x’s)
!  Characterise the inputs
Module 4 175
Classifying Inputs;
! Inputs can be classified as one of three types
! Controllable (C)
!  Things you can adjust or control during the process
!  Speeds, feeds, temperatures, pressures….
! Standard Operating Procedures (S)
!  Things you always do (in procedures or common sense things)
!  Cleaning, safety, etc.
! Noise (N)
!  Things you cannot control or do not want to control
(too expensive or difficult)

!  Ambient temperature, humidity, operator...
Module 4 176
Pareto analysis helps to identify the top 20% of causes that needs to be
addressed to resolve the 80% of the problems.
Module 4 177
The result of a Pareto analysis is Pareto Chart
Module 4 178
Performing a Pareto analysis
1. Identify and List Problems
2. Identify the Root Cause of Each Problem
3. Score Problems
4. Group Problems Together By Root Cause
5. Add up the Scores for Each Group
Module 4 179
Things to do when performing the analysis;
! Define the purpose of using the tool.
! Identify the most appropriate measurement parameters.
! Use check sheets to collect data for the likely major causes.
! Arrange the data in descending order of value and calculate % frequency
and/or cost and cumulative percent.

! Plot the cumulative percent through the top right side of the first bar.
! Carefully scrutinize the results. Has the exercise clarified the situation?
Module 4 180
Things to watch out for when doing a Pareto analysis;
! Misrepresentation of the data.
! Inappropriate measurements depicted
Lack of understanding of how it should be applied to particular problems

! 
! Knowing when and how to use Pareto Analysis

! Inaccurate plotting of cumulative percent data
Module 4 181
The cumilative Line;
! A Pareto chart with a steep cumulative line is better because in such a chart,
the value is concentrated in the left-most categories

A relatively flat cumulative bar is less helpful, because this arrangement
! 
indicates no problems as more important than the rest, or that it may have
been subdivided too much
In this case, regrouping into a few large categories may bring about a better
! 
result
Module 4 182
Project Management Basics – Project Metrics
Measures
!  Should be consistent with the problem statement and objectives
Primary Metric(s) - used to measure success

!  Needs to include 3 series, plotted as a function of time:
!  Baseline performance (average over past 12 months)
!  Actual performance
!  Objective / target performance
!  Examples:
!  Rolled throughput yield (RTY)
!  Process Sigma Level or Ppk
!  Defects per unit (DPU)
Module 4 183
Project Management Basics – Project Metrics
Secondary Metrics
! Secondary Metric(s) drive the right behaviour
! Tracks potential negative consequences or potential secondary positive
outcome
! More than one may be required
! Measurements of key input/output features, cycle time, or process
resource usage that may improve as a result of meeting objectives using

the primary metric
! Can be “Drivers” or “Riders” – i.e. Vital X’s impacting the project (Primary
Metric) or “Good Consequential Metrics”
Module 4 184
Project Management Basics – Project Planning Tools
Project planning tools include;
!  Gantt charts, also commonly know as MS Project Plans
!  Critical path method (CPM), usually overlaid on the Gantt chart
!  Program Evaluation and Review Technique (PERT) charts
!  Work Breakdown Structures
Module 4 185
A Gantt chart shows the relationships among the project tasks, along with
time constraints. The horizontal axis of a Gantt chart shows the units of time.
The vertical axis shows the activities to be completed. Bars show the
estimated start time and duration of the various activities. The critical path will
be highlighted
Module 4 186
PERT & CPM are used for project scheduling.
Project scheduling by PERT-CPM consists of four basic phases:
! 
!  Planning
!  Scheduling
!  Improvement
!  Controlling
! A network (or arrow) diagram is constructed with each activity being
represented by an arrow and graphically displays precedence
Module 4 187
PERT Chart
Module 4 188
Finding the Critical Path;
There are two time-values of interest for each event: its earliest time of
! 
completion and its latest time of completion

Slack time is the difference between the latest and earliest times for a given
! 
event. Thus, assuming everything else remains on schedule,

The slack for an event indicates how much delay in reaching the event can
! 
be tolerated without delaying the project completion

Activities with slack times of zero are said to lie on the critical path for the
! 
project. A critical path for a project is defined as a path through the network
such that the activities on this path have zero slack
Module 4 189
Work Breakdown Structure (WBS);
A process for defining the final and intermediate products of a project and
! 
their relationships
Goal is to reduce complex problems to a collection of discrete and
! 
manageable tasks
The WBS is represented as a tree diagram
! 
In the Define phase, WBSs are combined with Pareto analysis to organize
! 
problems before solutions are applied

In the Analyze phase, WBSs are used to organize all of the issues and
! 
complaints to be handled during the Improve phase
Module 4 190
Work Breakdown Structure (WBS);
Module 4 191
Project Management Basics – Project Documentation
Types of project documentation include;
Status reports
! 
Management briefings
! 
Story Boards
! 
Summary spreadsheets
! 
Module 4 192
Project Management Basics – Project Documentation
Story Boards
Summarizes project progress
! 
Basic format is based on DMAIC

! 
Demonstrates what tools have been applied in the course of defining,

! 
analyzing, and resolving the process problem

The storyboard should be kept up-to-date with the latest developments as a
! 
project progresses
Module 4 193
Project Management Basics – Project Risk
Management
! Project risk management is the art and science of identifying, analyzing, and
responding to risk throughout the life of a project and in the best interests of
meeting project objectives
! It can help improve project success by helping select good projects,
determining project scope, and developing realistic estimates

! KPMG study found that 55 percent of runaway projects—projects that have
significant cost or schedule overruns—did no risk management at all
! The goal of project risk management is to minimize potential negative risks
while maximizing potential positive risks
Module 4 194
Management
100%
80%
80%
60%
60% 47% 47% 43%
40% 35%
20% 6%
0%
te
ns
ps
ts
s
s
e
e
m
on
tia
en
ru
sli
ris
le
go
N
itm
er
p
e
ob
ov
ur
ul
ne
m
pr
ts
d
m
st
he
to
d
en
co
co
oi
sc
y
ev
av
ilit
ce
er
ce
Pr
ab
/
m
te
u
u
ed
to
a
ed
e
ip
us
ov
R
R
tic
tc
pr
An
Im
ee
M
*Kulik, Peter and Catherine Weber, “Software Risk Management Practices –

2001,” KLCI Research Group (August 2001).
Module 4 195
Management
Risk Management Process
! Risk management planning - Deciding how to approach and plan the risk
management activities for the project

! Risk identification - Determining which risks are likely to affect a project and
documenting the characteristics of each

! Qualitative risk analysis - Prioritizing risks based on their probability and
impact of occurrence
! Quantitative risk analysis - Numerically estimating the effects of risks on
project objectives using FMEA. The output is an RPN for each risk.
Module 4 196
Management
Risk Management Process.
! Risk response planning - Taking steps to enhance opportunities and reduce
threats to meeting project objectives

! Risk monitoring and control - Monitoring identified and residual risks,
identifying new risks, carrying out risk response plans, and evaluating the
effectiveness of risk strategies throughout the life of the project
The output of risk management planning is a risk management plan

! 
Module 4 197
Project Management Basics – Project Closure
Project Closure.
! Get sign-offs
! Archive the documentation
! Conduct lessons learned
! Close off the books

! And....
Module 4 198
End of Project Management Basics
! Project charter
Project scope
! 
Project metrics
! 
Project planning tools

! 
Project documentation
! 
Project risk analysis

! 
Project closure
! 
Module 4 199
Module 5 – Define Phase – Management & Planning Tools
Management & Planning Tools
Outline
1. Affinity diagrams,
2. Interrelationship diagrams
3. Tree diagrams
4. Prioritization Matrices
5. Matrix diagrams,
6. Process Decision Program Charts (PDPC)
7. Activity Network diagrams
Module 5 201
Affinity Diagram
•  Created in the 1960s by Japanese anthropologist Jiro Kawakita.
•  Tool for assimilating and understanding large amounts of information
•  Draw out common themes from a large amount of information
•  Discover all the hidden linkages
Module 5 202
How to Create an Affinity Diagram – Silent Brainstorming
!  Gather a group together
!  Individual silent brainstorming
!  Record each idea with a marking pen on a separate sticky note or card.
!  Need a complete statements
!  Each participant reads and randomly posts their ideas on the wall
!  Other participants can ask for clarification when an idea is read
!  Do not place the notes in any order. Do not try to determine categories or
headings in advance
!  After all ideas are posted begin Silent Consensus
Module 5 203
How to Create an Affinity Diagram – Silent Consensus
!  The entire team gathers around the posted notes
!  No talking during this step
!  Look for ideas that seem to be related in some way
!  Move the Post-Its and place them side by side
!  Repeat until all notes are grouped
!  Okay to have “loners” that don’t seem to fit a group
!  It’s all right to move a note someone else has already moved
!  If a note seems to belong in two groups, make a second note
Module 5 204
How To Create an Affinity Diagram - Clarification Step
! Participants can discuss the “results” of the chart
! Any surprising patterns?
! Any reasons for moving controversial notes
! A few more changes may be made
! When ideas are grouped, select a heading for each group
! Look for a note in each grouping that captures the meaning of the group. If
not create one

! Place it at the top of the group
! highlight headers notes in a bright color
! Combine groups into “super groups” if appropriate
! Want 6 – 10 headers
! Take the time to do this step – it is the foundation for the other tools
Module 5 205
Affinity Diagram Example
Issue Statement
Issues Affecting the High Staff Turnover
of Sunshine County Health Department
Header Cards:
Limited
Low Professional Low
Salary Development Morale
Work Public Health

Leadership
Environment Misunderstood
Module 5 206
Interrelationship diagrams
Identifies and explores causal relationships among related concepts or ideas
! 
Can address problems with a complex network of causes and effects.

! 
Identifies key drivers and bottlenecks

! 
Entries (nodes) in the diagram are called concerns

! 
A concern with a high number of output arrows is a key cause

! 
A key cause affects a large number of other items

! 
Use the strategic factors derived from your affinity diagram to develop the
! 
concerns for your interrelationship diagram.
Module 5 207
Interrelationship Diagraming Steps:
! Write each concern on a piece of paper in a circular pattern (allow room
between concepts)
! Number them to make comparison process easier to track
! Use pairwise comparisons (1-2, 1-3, 1-4…2-3, 2,4…3,4)
•  If there is a relationship draw arrow to effect

•  If there is no relationship leave blank
•  The can be no 2-way relationships
Module 5 208
Interrelationship Diagraming Steps (cont'd):
!  Analyze the diagram
!  Count the arrows (# out - # in)
!  Highest out are primary drivers or key causes
!  Resources here can produce pronounced change
!  Lowest are key bottlenecks
!  Affected by many other options
!  May be inhibiting other options from proceeding as required
!  Highlight primary drivers and key bottlenecks
Note: examine only cause and effect relationships. Likely will have arrows
! 
on only 50% of relationships

Module 5 209
Interrelationship Diagram example
® Certified Six Sigma Black Belt Handbook. Milwaukee, Wisconsin, ASQ Quality Press
Module 5 210
Interrelationship Diagram example
® Certified Six Sigma Black Belt Handbook. Milwaukee, Wisconsin, ASQ Quality Press
Module 5 211
Tree diagrams
Deconstruct a high-level entity, factor, deliverable or plan into its component
! 
elements or tasks
! Usage examples: deploy a quality plan, a work breakdown structure, or
develop objectives, policies and implementation steps
! Use the key drivers and bottlenecks identified from your interrelationship
diagram .
! Refer to ideas associated with that factor on your affinity diagram.
! Develop a tree diagram including this information, and expand it into several
next level strategies to meet these targets
Module 5 212
Creating a Tree Diagram
Work from left to right
! 
Start with the purpose to be accomplished

! 
Generate the high level targets or goals that must be completed to

! 
accomplish the purpose

Link each goal to the purpose (these are the first branches of the tree)
! 
Expand on each target to identify and define subordinate tasks to

! 
accomplish each target

Link each to their target
! 
Continue expansion process until final level is implementable.

! 
Review logic of completed tree (perhaps with larger group)

! 
Module 5 213
Tree Diagram Example
Key Driver Goals Strategies
Module 5 214*
Management Management & Planning Tools
Matrix Diagrams
Various types;
SMART Plan - Technique for structuring the task details when planning the
! 
implementation of a project. May use output from a WBS Tree

Correlation - Shows the relationship between one list of variables and
! 
another. Relationships are usually based on experience. Example is the

House of Quality
Matrix Data Analysis - Arranges a large array of numbers so that they may
! 
be visualized and comprehended easily
Module 5 215
Prioritization Matrix (aka Criteria Matrix)
!  Prioritizes issues, tasks, characteristics, based on weighted criteria using a
combination of tree and matrix diagram techniques
!  Prioritization matrices are designed to reduce the number of options to
consider before implementation planning occurs
Module 5 216
Prioritization Matrix (aka Criteria Matrix) Creation
1. Construct an L-Shaped matrix combining the options, which are the lowest-
level of detail of the tree diagram with the criteria
2. Determine the implementation criteria using any technique that will
satisfactorily weight the criteria
3. Prioritize the criteria using the weighting technique. Each team member
weights the criteria so the total weight equals 1, and the results are totaled
for the entire team.
4. Rank order the options in terms of importance by each criterion, average
the results, and round to the nearest whole number
5. Compute the option importance score under each criterion by multiplying
the rank by the criteria weight
Module 5 217
Prioritization Matrix (aka Criteria Matrix) Example
© Changing Minds
Module 5 218
Process Decision Program Charts (PDPC)
Maps out all contingencies when moving from statement of purpose to its
! 
realization
Typical applications
! 
!  Establishing an implementation plan for improvement project

!  To perform contingency planning
!  To anticipate problems and consider consequences
!  To determine possible countermeasures
Module 5 219
Process Decision Program Charts (PDPC)
! A type of Tree Diagram
! First level: purpose
! Second level: activities to be undertaken
! Third level: steps in these activities
! Fourth level: what ifs? (contingencies)

! Fifth level: countermeasures (contingency plans)
Module 5 220
Process Decision Program Charts (PDPC) Creation
1. The team refers to a previously completed data collection and analysis.
This data source can be a tree diagram, matrix diagram, a problem
specification, or some other tool reference.
2. The next step is to construct a PDPC chart as outlined in the example
Conversion of an Assembly Line to Work Cells .
3. First, list the project goal, followed by a lower level of primary activities
detailed further into required tasks . Ensure that all activities have been
considered from the data source.
Module 5 221
Process Decision Program Charts (PDPC) Creation
4. For each task or requirement, ask what-ifs. See example What if there is an
interruption in production output? What if there is equipment downtime?
5. For every what-if, consider what countermeasures can be taken. Connect
what-ifs and countermeasures to the tasks to complete the chart. Designate
countermeasures as practical and feasible = 0, or impractical and difficult = X.
6. Review the chart, make revisions if needed, and provide date of issue
Module 5 222
Process Decision Program Charts (PDPC) Symbols
Module 5 223
Process Decision Program Charts (PDPC) Example
Module 5 224
Activity Network Diagram
A diagram of project activities that shows the sequential and simultaneous
! 
relationships of those activities using arrows and nodes, as well as the

dependencies
It is used to identify a project’s critical path, as well as the most likely project
! 
completion time, the most optimistic time, and the most pessimistic time
It is useful to pictorially depict the dependencies and opportunities for
! 
schedule optimization of a project

Can only show finish-to-start dependencies
! 
In process management it is very useful for optimizing the process time

! 
Module 5 225
Activity Network Diagram Creation
1. First list down all the activities involved in the project
2. Find out the chronological order of the activities
3. Find out tasks that can be executed simultaneously
4. Arrows depict an activity, whereas the nodes depict the start and end of an
activity
5. There should be only a single Start and End Nodes for a project
6. Each task should be given unique node notations
7. Draw it out.
Module 5 226
Activity Network Diagram Creation
1. First list down all the activities involved in the project
2. Find out the chronological order of the activities
3. Find out tasks that can be executed simultaneously
4. Arrows depict an activity, whereas the nodes depict the start and end of an
activity
5. There should be only a single Start and End Nodes for a project
6. Each task should be given unique node notations
7. Draw it out.
Module 5 227
Activity Network Diagram Drawing it out
1. Find all of the activities that start at node 1. Draw their finish nodes and
draw arrows between node 1 and those finish nodes. Put the activity letter
or name and duration estimate on the associated arrow.
2. Continuing drawing the network diagram, working from left to right. Look for
bursts and merges. A burst occurs when a single node is followed by two or
more activities. A merge occurs when two or more nodes precede a single
node.
3. Continue drawing the project network diagram until all activities that have
dependencies are included in the diagram.
4. As a rule of thumb, all arrowheads should face toward the right, and no
arrows should cross in an AOA network diagram
Module 5 228
Activity Network Diagram Example
Module 5 229
Activity Network Diagram Calculations
1. First take note of which of the nodes will take the most amount of time, and which of
those nodes will to take the least amount of time
2. The Critical Path is a line that goes through all of the nodes that have the longest
expected completion times.
3. The expected completion time as defined by the critical path is know as the Most
Likely Time
4. To come up with the Most Optimistic Time, decide upon the shortest possible time
for each of the nodes, and then add those up
5. To come up with the Pessimistic Time decide upon the longest possible time for
each of the nodes, and then add those up
Module 5 230
Activity Network Diagram Calculations
1. Expected Time = Optimistic + (4*Most Likely) + Pessimistic
6
2. Limits of Expected Variation = Optimistic – Pessimistic

6
Module 5 231
End
In this module we covered
!  Affinity diagrams,
!  Interrelationship diagrams
!  Tree diagrams
!  Prioritization Matrices
!  Matrix diagrams,
!  Process Decision Program Charts (PDPC)
!  Activity Network diagrams
Module 5 232
Module 6 – Define Phase – Business Results for Projects
Business Results for Projects
Outline
1. Process Performance
2. Communication
Module 6 234
Business Results for Projects - Process Performance
Sigma Levels and Defects Per Million Opportunities (DPMO)
!  Six Sigma uses the DPMO level of a process to generate a Sigma
level for the process

!  It uses the standard normal distribution as its measurement system
!  A Sigma level compares the variation in process performance to the
acceptable levels set by the customer

!  The higher the Sigma level the better. Six Sigma performance of 3.4
DPMO
WARNING: The normal distribution and DPMO will not apply if special
causes are dominant within the process
Module 6 235
Six Sigma uses the standard normal distribution as its measurement
system
The mean is µ and the standard deviation is denoted by σ.
Module 6 236
! Note that theoretically Six Sigma applied to a normal distribution is
actually 0.002 DPMO

! However Sigma levels are calculated using an inbuilt 1.5 σ shift for the
process average
! This allows for the natural propensity of processes to drift
! The DPMO are calculated first and then translated into a Sigma value
via a conversion table (see next slide)

! Formula for DPMO where Number of Units is n, Number of Defects is
d, Number of Defect Opportunities is o
Module 6 237
Sigma Level Conversion Table
Module 6 238
First Pass Yield (YFP )
!  A YFP is the fraction of units produced by a sub-process without a defect
First Pass Yield will be used to calculate process sigmas
!  Calculate as follows:
!  For a given sub-process: the defect opportunities (o ) are defined (based

on customer needs & requirements), a given number of units (n ) are
chosen, and the total number of defects (d ) are counted
!  For discrete attributes, the number of opportunities where a “Pass/Fail”
judgment was made is counted as d, for continuous attributes; the number
of opportunities where the specification limit(s) were exceeded is counted
as d
Module 6 239
Normalized Yield (Ynorm )
!  A Y norm is the fraction is a “rolled-up” weighted average of the sub-
process First Pass Yields for an end-to-end process
!  This measure permits comparisons across different business processes
and across processes of varying complexity
!  A “rolled-up” process sigma can be calculated from Normalized Yield
(convert the yield value to a percentage and use the table on slide 6
!  To calculate; use o, n, and d. As well I = the number of subprocesses
Module 6 240
Rolled Throughput Yield (Y RTP or RTY)
Is the probability of a “unit” going through all the processes without a defect
! 
Is the product multiplying the First-Pass Yields of each sub-process

! 
Generally used for internal monitoring of business processes and for

! 
prioritizing improvement projects

Best measure of the effectiveness and efficiency of business processes
! 
DO NOT convert to a sigma value as it results in a negative sigma.

! 
Module 6 241
Non-normal Data
!  The sigma and yield relationships shown on the table on slide 6 are based
on the normal distribution
!  DO NOT misinterpret this to mean that only normally distributed data can be
used to calculate a sigma – there is an alternative.
!  In some cases, the non-normal data can be transformed to a normal
distribution via logarithms to a normal distribution
.
Module 6 242
Cost of Poor Quality (COPQ)
!  As a Green Belt, one of your tasks will be to estimate COPQ for your
process
!  Through your process exploration and project definition work you will
develop a refined estimate of the COPQ in your project
!  This project COPQ represents the financial opportunity of your
team s improvement effort (VOB)
!  Calculating COPQ is iterative and will change as you learn more
about the process
Module 6 243
Cost of Poor Quality (COPQ)
!  COPQ helps us understand the financial impact of problems created by
defects.
!  COPQ is a symptom, not a defect
!  Projects fix defects with the intent of improving symptoms.
!  The concepts of traditional Quality Cost are the foundation for COPQ.
!  External, Internal, Prevention, Appraisal
!  A significant portion of COPQ from any defect comes from effects that are
difficult to quantify and must be estimated.

!  Need to uncover and understand the hidden factory and other sources
of waste
Module 6 244
244
Internal COPQ
!  Rework
!  Rejected supplier parts and materials
!  Inspection
!  Etc..
External COPQ
!  Returns
!  Warranty work
!  Loss of Customers
!  Etc...
Module 6 245
245
While hard savings are always more desirable because they are easier
to quantify, it is also necessary to think about soft savings
COPQ – Hard Savings COPQ – Soft Savings
•  Labor Savings •  Gaining Lost Sales

•  Cycle Time Improvements •  Reduced Law Suites
•  Scrap Reductions •  Customer Loyalty
•  Hidden Factory Costs •  Strategic Savings
•  Inventory Carrying Cost •  Preventing Regulatory Fines
Module 6 246
246
COPQ Prevention
!  Error Proofing
!  Supplier Certification
!  DFSS
!  Etc..
COPQ Detection
!  Supplier Audits
!  Rejected parts
!  Logged rework
!  Etc...
Module 6 247
247
Process Capability Index
!  Quantifies the ability of a process to meet the expectations of
customers and other stakeholders

!  Key to decision-making related to design for manufacture is the
understanding of not only the requirements of the process, but also

what the process is able to achieve (process capability)
Module 6 248
Process Capability Index
!  Usually converted into a standard deviation or DPMO. In the Measure
phase, process capability indices can create a baseline estimate for a

controlled process
!  In the Improve stage, a process capability index can confirm process
improvement
!  In the control stage, these indices are used to monitor processes to
confirm they remain in a state of statistical control

!  Given the above, process capability indices must only be created
after a state of statistical control is established
Module 6 249
Process Capability Index Creation
!  First use a control chart to determine the stability of the process.
Proceed only if the process is in a state of statistical control

!  The first calculation we need to make is the process potential. This is
denoted Cp
!  Cp compares the process spread to the width of the tolerances. If the
tolerances are wider than the process spread then potentially the
process can achieve what is being asked of it
!  The tolerances are denoted UTL (Upper spec) and LTL (Lower spec)
Module 6 250
Process Capability Index Creation
!  Cp in itself is insufficient as it would not, for example distinguish
between processes that have the same spread and Cp also takes no
account of setting
!  Cpk addresses these issues by taking account of setting and the
likelihood of producing non-conforming product for the process

!  Cp and Cpk together compare the distance from the process centre
to either tolerance against the distance from the process centre to the
top or bottom of the process
!  We take the worst case in order to establish the overall Cpk
OR Whichever is lower
Module 6 251
Process Capability Index Interpretation
!  Cpk's best achievable value is to equal Cp
!  This will occur when the process is equidistant from the two limits (i.e.
the process is exactly on target)

!  It is not possible for Cpk to exceed Cp
!  It is perfectly possible for Cpk to take a negative value if the centre of
the process is outside one of the tolerances

!  A Cpk of 1 indicates that the process is operating at a minimum level
of capability (i.e. at least one end of the process is bang up against a

tolerance)
!  Less than 1 means an incapable process
!  The aim should always be for Cp = Cpk
Module 6 252
Process Capability Index Interpretation (con't)
!  The aim should always be for Cp = Cpk (i.e. properly centered)
!  By using the properties of the normal distribution it is possible to
predict percentages out of tolerance for any given capability value

provided that the process is:
!  Stable
!  Normally distributed
!  Properly centered (Cp = Cpk)
Note: Due to its composite nature it is less helpful in showing what has
to change
Module 6 253
Process Capability Improvement
!  The approach to improving process capability is essentially about
reducing common cause variation

!  This will mean action on the process relating to things such as
operator training,machine maintenance, fixturing etc
Module 6 254
Business Results for Projects - Communication
!  Effective Communication is key to a successful Six Sigma project.
!  Communications is conducted both formally and informally
!  Effective communication involves understand the characteristics of
both formal and informal communication
!  Formal communication is the flow of communication within the chain
of command
!  Informal communication is all other communication within the
organization
Module 6 255
Top-Down Communication
! One of the three formal channels

! Flows from higher to lower levels
! Key aspect—subordinates react most effectively to those matters
judged to be of the greatest interest to the boss

! Selective screening is a problem
! Example forms: job instructions, memos, policies, procedures,
manuals, etc.
Module 6 256
Bottom-Up Communication
! One of the three formal channels
! Flows from lower to higher levels
! Most ineffective of the three channels
! Employees need opportunities to be:
!  Heard
!  Anonymous
! Example devices: suggestion boxes, group meetings, participative
decision making, grievance procedures, etc
Module 6 257
Horizontal Communication
!  One of the three formal channels
!  Flows from one level to an equal level
!  Necessary for coordination of diverse organizational functions
!  Most effective of the three channels
!  Example devices: Internet, corporate intranets
Module 6 258
Horizontal Communication
!  One of the three formal channels
!  Flows from one level to an equal level
!  Necessary for coordination of diverse organizational functions
!  Most effective of the three channels
!  Example devices: Internet, corporate intranets
Module 6 259
Informal Communication
! Communications within organizations do not necessarily follow the
formal pathways
! Most organizations have extensive networks of informal
communications
! Since they are ingrained into organizational life, you should use them
to benefit your Six Sigma initiatives

! Elements of informal channels are:
!  Grapevine—75% accurate
!  Management by wandering around
!  Rumor—unverified belief in general circulation
Module 6 260
Barriers to Communication
!  Interpersonal barriers which include problems with emotions and
perceptions held by employees

!  Selecting the wrong channel for sending a message
!  Semantics
!  Sending inconsistent cues between verbal and nonverbal
Module 6 261
Barriers to Communication
!  Organizational barriers
!  Status and power differences between lower and higher levels
!  Differences across departments of needs and goals
!  The communication flow may not fit the group's or organization's
task
!  Formal channels may not be available for upward, downward,
and horizontal communications
Module 6 262
End
Business Results for Projects
Process Performance
! 
Communication
! 
Module 6 263
Module 7 – Define Phase – Team Dynamics and Performance
Team Dynamics and Performance
Outline
1. Team stages and dynamics
2. Team roles and responsibilities
3. Team tools
4. Team Communication
Module 7 265
Team Stages and Dynamics
!  There are four stages of team development; Forming, Storming, Norming,

and Performing
!  Knowledge of these stages and strategies for moving through these stages
help team members to promote more effective collaborative processes
Module 7 266
Team Stage 1; Forming
!  Definition: Stage 1 teams are generally new teams that are learning how to
work together
!  Characteristics of stage 1 teams: Members tend to be tentative and
polite and to have little conflict
!  Critical skills and activities: Stage 1 teams need to identify their purpose,
develop group norms, identify group processes, define roles, build
relationships and trust
!  Role of facilitator/leader: Stage 1 teams usually need a strong leader who
can help the team go through its forming activities
Module 7 267
Team Stage 2: Storming
! Definition: Stage 2 teams have moved past the early forming stages and
are now encountering some disagreements and/or conflict. This is natural, but
teams need to find effective ways to handle conflict before they can move on
to stage 3.
! Group characteristics: Members of stage 2 teams tend to exhibit
increased conflict, less conformity and “jockeying” for power.

! Critical skills and activities: Stage 2 teams need to learn how to resolve
conflict; clarify their roles, power, and structure; and build consensus through
re-visiting purpose.
! Role of leader(s): Stage 2 teams need leaders and other team members
who are willing to identify issues and resolve conflict
Module 7 268
Team Stage 3: Norming
!  Definition: Stage 3 teams have successfully moved out of the
storming stage and are ready to move to a higher level of
communication and problem-solving.
!  Group characteristics: Members of stage 3 teams demonstrate an
improved ability to complete tasks, solve problems, resolve conflict.
!  Critical skills and activities: Stage 3 teams need to learn to
engage in more sophisticated problem-solving and decision-making,
continue the use of effective strategies for conflict resolution and
take greater levels of responsibility for their roles
!  Role of leader(s): In stage 3, leaders become less directive, team
members feel empowered, and multiple leaders emerge
Module 7 269
!  Team Stage 4: Performing
!  Definition: Stage 4 teams are at the highest level of performance and can
process their strengths and weaknesses while accomplishing their goals.
!  Group characteristics: In stage 4, the team takes a flexible approach to
roles and structures depending on the task at hand. The team is able to
evaluate its effectiveness and views conflict is viewed as an opportunity.
Stage 4 teams tend to be energetic, creative, and fun!
!  Critical skills and activities: Stage 4 teams need to hold high
expectations for their performance. They often use sub-groups as well as
the large group for decision-making and task completion. Teams also
recognize the need to ensure that all members are in agreement with the
role and purpose of sub-groups.
!  Role of Leader: In a stage 4 team, it’s often difficult to identify the leader,
because everyone is sharing in leadership
Module 7 270
During the Storming stage team members:
!  Realize that the task is more difficult than they imagined
!  Have fluctuations in attitude about chances of success
!  May be resistant to the task

!  And have poor collaboration
Questions to ask:
!  Do we have common goals and objectives?
!  Do we agree on roles and responsibilities?
!  Do our task, communication, and decision systems work?
!  Do we have adequate interpersonal skills?
Module 7 271
During the Storming stage:
! Separate problem issues from people issues
! Be soft on people, hard on problem
! Look for underlying needs, goals of each party rather than specific solutions
State your views in clear non-judgmental language.

! 
Clarify the core issues

! 
Listen carefully to each person’s point of view

! 
Check understanding by restating the core issues

! 
Module 7 272
Storming stage – Five Responses to Conflict
Avoidance - the least cooperative and assertive way to resolve a conflict,
though ok if the issue is insignificant
Accommodation - can be a valuable tool in conflict resolution, as long as it
does not engender resentment
Competition - Can be a great way to settle disputes and generate excellent
work as long as it doesn't get out of hand
Compromise - useful response to conflict when maintaining team harmony is
more important than coming up with the best possible solution
Collaboration - an effective style of conflict resolution when both parties
have good points. Also is appropriate when members of a team have different
areas of expertise, and so it is a good idea to combine their perspectives
Module 7 273
Team Roles and Responsibilities
Champion
Takes a very active sponsorship and leadership role in conducting and implementing
! 
Six Sigma projects

Can be the Senior Executive
! 
Champions should:
! 
!  Identify the project on the organizational dashboard

!  Provide an ongoing communication link between the project team and
Executive committee
!  Keep the team focused on the project by providing direction and
guidance
!  Assure that Six Sigma methods and tools are being used in the project
Module 7 274
Master Black Belt
Takes a leadership role as keeper of the Six Sigma process and advisor to executives
! 
or business unit managers

Master Black Belt should:
! 
!  Counsel senior executives and business unit managers on Six Sigma

management
!  Continually improve and innovate the organization’s Six Sigma process
!  Apply Six Sigma across across both operations and transactions-based
process
!  Mentor Green Belts and Black Belts
Module 7 275
Black Belt
!  Is a full time change agent and improvement leader.
!  Black Belts should:
!  Communicate with the champion and process owner about progress of
the project
!  Help team members design and analyze experiments
!  Provide training in tools and team functions to project team members
!  Coach Green belts leading projects limited in scope
Module 7 276
Green Belt
! Is an individual who works on projects part time, either as a team member for
complex projects or as a project leader for simpler projects

Green Belts should:
! 
!  Define & review project objective with project’s champion

!  Facilitate the team through all phases of the project
!  Analyze data through all phases of the project
!  Train team members in the use of Six Sigma tools and methods through
all phases of the project
Module 7 277
Team tools - Brainstorming
!  Brainstorming can be used to identify alternatives, obtain a complete list of

items and to solve problems.
!  There are a variety of brainstorming techniques.
!  The common principle of brainstorming is to set aside the restrictive

thinking processes so that many ideas can be generated. A good way to do
that is silent brainstorming
Module 7 278
Team tools – Brainstorming
Brainstorming can:
Break through traditional thinking about a problem.
! 
Generate new ways of thinking.

! 
Provide an environment for building on new ideas.

! 
Reduce the tendency to prematurely discard new ideas.

! 
Facilitate team building.

! 
Encourage team problem solving

! 
Module 7 279
Team tools - Nominal Group Technique (NGT)
Normally implemented in six stages:

1. Participants are first presented by the session moderator in which an initial
statement of the topic area to be discussed
2. They are then directed to reflect individually on the topic
3. The group moderator asks a participant to state one of the responses he or
she has arrived at
4. The next stage involves consolidation and review of the ideas
5. They are then requested to establish the relative importance that should be
accorded to each of the response ideas
6. The final stage is the compilation of the results
Module 7 280
Team tools - Nominal Group Technique (NGT)
The analysis of NGT data involves both qualitative and quantitative

procedures requiring four basic steps:
1. Categorization of initial problem statements into problem themes
2. Regrouping of problem themes within conceptual model to form major
problem dimensions
3. Calculation of a score or index reflecting the importance of each problem
theme
4. Ranking of problem themes according to their importance index
Module 7 281
Team Communication
The Six Sigma team uses the usual forms of communications; both within the
team and out to other teams and stakeholders. These include:
!  Status reports and status meetings
!  E-Mail, Phone, and face-to-face meetings
!  Project Wiki and Sharepoint
!  Other project documentation and information radiators
!  Meetings and interviews on specific topics
Module 7 282
End
!  Team stages and dynamics
!  Team roles and responsibilities
!  Team tools
!  Team Communication
Module 7 283
Define Phase – Summary & Review Questions
Define Phase – Summary
!  Identify a process to improve
!  Identify the customer (internal or external)
!  Outline the customer’s critical to quality (CTQ) parameter(s)
!  Set our improvement goals
!  Identify other stakeholders
!  Develop a business case
!  Define a high-level as-is state of the business process
!  Gain consensus on the business case and mobilize the required resources
!  Develop a high-level process map
!  Plan our Six Sigma project
Define Summary & Review
Questions
Define Phase – Summary
Questions to Ask at Phase End
!  Will our customers relate to our CTQ list?
!  Are we working on the critical X's?
!  What sources of information and data are we using?
!  What is our As Is SIPOC?
!  Do we have consensus and buy in from our key stakeholders?

Questions
Define Phase – Review Questions
Define Phase Review Question #1
A shoe manufacturing firm learned through a Six Sigma project their boot
soles could be made of a different material requiring two less steps in the
process. Removal of these two steps yielded a monthly cost savings of
$7,500. Therefore the reported annual financial savings for this SS project
were _____________.
a. $45,000
b. $75,000
c. $90,000
d. $120,000

Questions
A GreenBelt utilized a diamond symbol in a Process Map she created for the
process. By use of the diamond symbol she was showing a(n)
_______________ point in the process
a. Ending
b. Beginning
c. Decision
d. Repair station

Questions
When in the process of trying to identify the Critical X’s for a GreenBelt
creates a(n) _____________ because frequently it is 20% of the inputs that
have an 80% impact on the output.
a. Pareto Chart
b. FMEA
c. Np Chart
d. X-Y Diagram

Questions
Define Phase Review Question Answers
1. C $90,000
2. C Decision
3. A Pareto Chart

Questions
Module 8 – Measure Phase – Process Analysis and
Documentation
Module 8 – Measure Phase –
Process Analysis and Documentation
Outline
1.  Measure Phase Overview
2.  Process Analysis and Documentation
Module 8 292
Measure Phase
!  The team will focus on gathering the information necessary to complete the
project
!  First, the team will attempt to define each relevant process in great detail
!  It will be necessary to develop a group of metrics appropriate to the
processes
!  No metric is complete until accompanied by a measurement analysis
system that identifies and quantifies any common errors in the metric
!  The final general objective of the measure phase is to estimate process
baselines
Module 8 293
Process Maps
!  Process maps and the mechanics of creating them were described in
Module 2
!  In the Measure phase, they are used to record the lower process levels and
reveal differences in the perceptions of shareholders
!  Process maps are good at finding process complexities, shareholders, and
inefficient locations
!  The goal of process maps is to spot redundant, unnecessary decisions and
tasks and to discover ways to simplify processes
Module 8 294
Flow Charts
!  A standard diagramming technique that most people are familiar with
!  In the Measure phase, flowcharts can be used to map a process as it is
currently being performed or to identify how different shareholders perceive
a particular process or problem
!  Look for a preponderance of decision points, as this may lead to
unnecessary delays or adverse variations
Module 8 295
Analyze Work Documents
!  Deconstructing the process from manuals, and other instruction or training
documents
!  Use to produce the various process and work flow diagrams
!  Danger is that actual process may deviate from the documented process so
best to observe and record the actual process
Module 8 296
END
!  Measure Phase Overview
!  Process Analysis and Documentation
Module 8 297
Module 9 – Measure Phase – Probability and Statistics
Probability and Statistics
Outline
1. Basic Probability Concepts
2. Central Limit Theorem
Module 9 299
Probability and Statistics - Basic Concepts
Statistical Notation – Cheat Sheet
Summation An individual value, an observation
The Standard Deviation of sample data A particular (1st) individual value
The Standard Deviation of population data For each, all, individual values
The variance of sample data The Mean, average of sample data

The variance of population data
The grand Mean, grand average
The range of data
The Mean of population data
The average range of data
Multi-purpose notation, i.e. # of subgroups, A proportion of sample data
# of classes
A proportion of population data
The absolute value of some term
Sample size
Greater than, less than
Greater than or equal to, less than or
Population size
equal to
Module 9 300
300
Normal Distribution
The normal distribution provides the basis for many statistical tools and techniques.
Definition
•  A probability distribution where the most frequently occurring value is in the
middle and other probabilities tail off symmetrically in both directions. This shape
is sometimes called a bell-shaped curve
Characteristics
•  Curve theoretically does not reach zero; thus the sum of all finite areas total less
than 100%
•  Curve is symmetric on either side of the most frequently occurring value
•  The peak of the curve represents the center, or mean, of the process
•  For practical purposes, the area under the curve represents virtually 100% of the
variation the process is capable of producing
Module 9 301
Every Normal Curve can be defined by two numbers:

• Mean: a measure of the center, also known as the average
• Standard deviation: a measure of spread
µ
Module 9 302
Parameters to describe spread
!  Range - Difference between highest and lowest value of the distribution

Influenced by Outliers
!  Variance - Average squared difference of data point from the average
!  Standard Deviation - Square root of the variance
Module 9 303
Terms;
! Population: All the items that have the property of interest under study
! Frame: An identifiable subset of the population
! Sample: A significantly smaller subset of the population used to make an
inference
! Mode: the most common value
Median :The value which comes half way when the data are ranked in order
! 
Trimmed Mean: Is calculated by eliminating a specified percentage of the

! 
smallest and largest observations from the data set and then calculating the
average of the remaining observations
Module 9 304
Probability and Statistics – Basic Concepts
Formulas
Standard Deviation - Sample
Standard Deviation - Population
Module 9 305
305
Formulas
Mean – Sample
Mean - Population
Module 9 306
306
Formulas
Variance – Sample
Variance - Population
Module 9 307
307
Formulas
Standard Error
Module 9 308
308
Probability and Statistics – Central Limit Theorem
Central Limit Theorem (CLT)
!  Asserts that the probability distribution of the sample means will

approach a normal distribution as the number of samples increases;
provided that they are simple random samples of uniform size
!  Applied in cases when the number of samples is relatively small or when
the true distribution is unknown
!  After about thirty samples, the data should approximate a normal
distribution
!  The central limit theorem is the basis for the most powerful of statistical
process control tools, Shewhart control charts
Module 9 309
309
Confidence Interval (CI)

•  A confidence interval estimate of a parameter consists of an interval of
numbers along with a probability that the interval contains the unknown
parameter
•  The level of confidence in a confidence interval is a probability that
represents the percentage of intervals that will contain if a large number
of repeated samples are obtained
•  For example, a 95% level of confidence would mean that if 100
confidence intervals were constructed, each based on a different
sample from the same population, we would expect 95 of the intervals
to contain the population mean
•  Based on the premise of CLT – with enough samples your CI should be
95% (normal distribution)
Module 9 310
310
Calculating Confidence Interval
There are four steps to constructing a confidence interval:

1.  Identify a sample statistic. Choose the statistic (e.g, sample mean,
sample proportion) that you will use to estimate a population parameter
2.  Select a confidence level. As we noted in the previous section, the

confidence level describes the uncertainty of a sampling method. Often,
researchers choose 90%, 95%, or 99% confidence levels; but any
percentage can be used
Module 9 311
311
Calculating Confidence Interval
3.  Find the margin of error. Often, however, you will need to compute the
margin of error, based on one of the following equations.
!  Margin of error = Critical value * Standard deviation of statistic
!  Margin of error = Critical value * Standard error of statistic

1.  Specify the confidence interval. The uncertainty is denoted by the
confidence level. And the range of the confidence interval is defined by
the following equation.
Confidence interval = sample statistic + Margin of error
Module 9 312
312
Hypothesis Testing
!  A statistical testing of a hypothesis – H

!  The alternative or default hypothesis is: HA
!  A probability is established to test the “null” hypothesis (no relationship
between two measured variables)
!  95% confidence: would mean that there would need to be 5% or less
probability of getting the null hypothesis; the null hypothesis would then
be dropped in favor of the “alternative” hypothesis
Module 9 313
313
End
Probability and Statistics
!  Basic Probability Concepts
!  Central Limit Theorem
Module 9 314
Module 10 – Measure Phase – Statistical Distributions
Statistical Distributions
Outline
1.  Statistical Distributions
Module 10 316
Normal Distributions
!  A continuation of the discussion on normal distribution from module 9
!  What makes a distribution normal?
!  Only random error is present
!  Process free of assignable cause
!  Process free of drifts and shifts
Module 10 317
The Normal Curve is a smooth, symmetrical, bell-shaped curve,
generated by the density function
Module 10 318
Each combination of Mean and Standard Deviation generates a unique
Normal Curve:
Standard Normal Distribution
Has a µ = 0, and σ = 1
! 
! Data from any Normal Distribution can be made to

fit the standard Normal by converting raw scores
to standard scores
! Z-scores measure how many Standard Deviations from the Mean a
particular data-value lies
Module 10 319
Empirical Rule
!  68.27% of the values lie within one standard deviation of the mean
!  95.45% of the values lie within two standard deviations of the mean
!  99.73% of the values lie within three standard deviations of the mean
Module 10 320
Binomial Distributions
!  Binomial distributions are useful when the units in a population exist in only
two states.
!  A binomial distribution only applies when trials are independent and the
number of samples in the population is fixed.
!  In a binomial distribution, the distributional parameter is the average
proportion
!  This value is assumed or calculated by dividing the number of sample items
that meet the condition by the total number of items in the sample
Module 10 321
Binomial Distribution vs. Normal Distribution
Module 10 322
Poisson
!  Poisson distribution can guess the number of times a particular condition
will occur for a given process or population; such as non-conforming units
!  The distinguishing feature of the Poisson distribution is its appropriateness
for situations in which the targeted condition may occur more than once in
each unit
!  The Poisson distribution accurately estimates the number of events in each
sample unit
!  The trials be should be independent, and the data should be composed of
positive whole numbers.
!  The distributional parameter is the average number of instances per unit
Module 10 323
Poisson Distribution Plot
© Wikipedia
The horizontal axis is the index k, the number of occurrences. The CDF is discontinuous at the integers of k
and flat everywhere else because a variable that is Poisson distributed can only take on integer values
Module 10 324
Poisson Distribution Formula
A discrete random variable X is said to have a Poisson distribution with
parameter λ > 0, if, for k = 0, 1, 2, …, the probability mass function of X is
given by:
where
e is Euler's number (e = 2.71828...)
k! is the factorial of k
The positive real number λ is equal to the expected value of X and also to its
variance
Module 10 325
Chi Square
A goodness-of-fit tests used measure the validity of a statistical assessment
!  Chi-square analysis is primarily used to deal with categorical (frequency)
data
!  We measure the “goodness of fit” between our observed outcome and the
expected outcome for some variable

!  We see if observed frequencies of occurrence in each group are
significantly different from expected frequencies

!  Important point about the non-directional nature of the test, the chi-square
test by itself cannot speak to specific hypotheses about the way the
results would come out. Not useful for ordinal data because of this
Module 10 326
Chi Square
! Usually, the higher the chi-square statistic, the greater likelihood the finding
is significant, but you must look at the corresponding p-value to determine
significance
! Many datasets encountered in Six Sigma have normal or approximately
! normal distributions. It can be shown that in these instances the distribution
! of sample variances has the form (except for a constant) of a chi-square
! distribution
! Chi square requires that there be 5 or more in each cell of a 2x2 table and
5 or more in 80% of cells in larger tables. No cells can have a zero count
Module 10 327
Chi Square Formula
Where Chi Square is

! 
Module 10 328
Chi Square – Degree of Freedom (df)
!  The number of independent ways by which a dynamic system can move

without violating any constraint imposed on it, is called degree of freedom
!  The degree of freedom can be defined as the minimum number of
independent coordinates that can specify the position of the system
completely
Module 10 329
Chi Square Table
! Used to determine P value
! The first row of numbers indicates probability.
! For your degrees of freedom (df) read across that row until you find the
next smallest number.

! Then go to the top and find the probability (P value)
Module 10 330
Student’s t
It is used to express confidence intervals for a set of data and to statistically
! 
compare the results of different experiments

The t test is also valuable to compare two different sets of data to determine
! 
if they are ‘the same’ or ‘different

Similar to Standard normal distribution
! 
Larger spread about zero due to increased variability due to using a sample
! 
rather than the population

Uses a critical values under the t distribution table
! 
Module 10 331
Student’s t
Assumptions
Population is normal although this assumption can be relaxed if sample size
! 
is “large”
Random sample was drawn from the population of interest
! 
As the sample size increases (degrees of freedom increases) the t

! 
distribution approaches the standard normal distribution

If the absolute value of the test statistic is greater than the critical value ,
! 
then we reject the null hypothesis
Module 10 332
t distribution
standard normal distribution
Module 10 333
Student’s t Distribution Critical Value
The critical value t with probability p lying to its right is found by looking up
on a t Distribution Critical Values Table
Module 10 334
Student’s t Distribution Critical Values Table (1-tailed)
Use the row corresponding to df and the column corresponding to p
Better yet use Excel's TINV() though double the probability as it generates 2-
tailed results
Module 10 335
F Distribution
!  This test can be used to either,
!  Test the equality of population variances
!  Test the equality of population means in ANOVA
!  Tests for regression models (slopes relating one continuous
variable to another
!  There is a different F distribution for every possible pair of degrees of
freedom
!  There are two sample variances involved and two sets of degrees of
freedom
!  The expected value of any F distribution is 1 if the null hypothesis is true
Module 10 336
F Distribution Formula
!  Let be the variance of the first sample and be the variance of the
second sample. The two samples need not have the same sample size.
!  F is the F distribution.
Module 10 337
F Distribution Curve
Module 10 338
End
! 
Module 10 339
Module 11 – Measure Phase – Collecting and Summarizing Data
Collecting and Summarizing Data
Outline
1.  Types of data and measurement scales
2.  Sampling and data collection methods
3.  Descriptive statistics
4.  Graphical methods
Module 11 341
Types of data
Attribute Data (Qualitative)
!  Is always binary, there are only two possible values (0, 1)
Variable Data (Quantitative)
!  Discrete (Count) Data
!  Can be categorized in a classification and is based on counts.
!  Takes on only a finite number of points that can be represented by the
non-negative integers
!  Continuous Data
!  Can be measured on a continuum,
!  It has subdivisions that are meaningful, such as; Time, Pressure,
Conveyor Speed, Material feed rate and Money
!  Always more desirable
!  In some cases Attribute Data can be converted to Continuous
Module 11 342
342
Data Scale Definitions

•  Nominal Scale – data consists of names, labels, or categories. Cannot be
arranged in an ordering scheme. No arithmetic operations are performed for
nominal data
•  Ordinal Scale – data is arranged in some order, but differences between data
values either cannot be determined or are meaningless
•  Interval Scale – data can be arranged in some order and for which differences
in data values are meaningful. The data can be arranged in an ordering
scheme and differences can be interpreted.
•  Ratio Scale – data that can be ranked and for which all arithmetic operations
including division can be performed. (division by zero is of course excluded)
Ratio level data has an absolute zero and a value of zero indicates a complete
absence of the characteristic of interest.
Module 11 343
343
Sampling and data collection methods
!  One of your first decisions in the sampling arena is the type of study or
question(s) you have
!  Take into account the rate of change of the process, the faster the process,
the more frequent should be the sampling
!  Another factor is the number/value of items produced between samples as
there is a risk of missing a problem
!  A sampling pattern that is too regular runs the risk of adversely affecting the
randomness of our sample and inadvertently syncing with some unknown
cycle
!  Always ensure that sampling plans and data collection plans are properly
documented
Module 11 344
Sampling must be:
! Representative of all segments (for example, locations, sizes, days of the

week, months, or shifts)
! Of adequate size;
!  Average or Standard Deviation - 30

!  Proportion Defective (P) – 300
!  Histogram, Scatter Diagram or Pareto chart – 50-100
!  Control Chart – 25-35
! Free from bias
Module 11 345
The 5 basic sampling methods
1. Simple Random Sampling - When every unit in the population has the
same chance of being selected
2. Stratified Sampling - When the population is divided into groups and a
sample is taken from each of the groups
3. Systematic Sampling - Some criteria or method exists regarding the
selection of samples. For instance, every 10th. unit might be selected
4. Cluster Sampling - A representative group is selected out of the
population, and then a random sample is drawn from that group
5. Judgment Sampling - Relies on expert opinions in their selection of a
sample group. This mode of sampling is appropriate when the samples
must have particular characteristics not common to every member of the
population
Module 11 346
Data Collection Plan
! Provides a documented strategy for gathering the data
! Answers questions like;
!  What data do we need?

!  What is the time frame for collecting them?
!  Who will collect the data?
!  Using what mechanism?
! Needs to ensure that the collection process yields accurate and relevant
data
Module 11 347
Check Sheets
! A check sheet is a custom-designed tally sheet to collect data on frequency
of occurrence
! A simple and effective way to display data
! Provides a uniform data collection tool
! Use when the data can be observed and collected repeatedly by either the
same person or the same location

! Also effective for collecting data on frequency and identifying patterns of
events, problems, defects, and defect location, and for identifying defect
causes
! Come in three forms; tally sheets, location check sheets and graphical or
distribution check sheets
Module 11 348
Check Sheets
! Tally Sheets are commonly used to collect data on quality problems and to
determine the frequency of events
! Location Check Sheets are a diagram of the part or item where the
defects are marked; a familiar example is the rental car diagram where you
mark any damage. A variation is marking any error on a document on the
document itself
Module 11 349
Check Sheets
Graphical or Distribution Check Sheets using a graphical form, the
! 
person collecting the data is able to visualize the distribution of the data.
© Changing Minds
Module 11 350
Data Coding
!  A systematic way in which to condense extensive data sets into smaller
analyzable units through the creation of categories and concepts derived
from the data
When to code;
!  When testing a hypothesis (deductive), categories and codes can be
developed before data is collected.
!  When generating a theory (inductive), categories and codes are generated
after examining the collected data
Module 11 351
Data Coding
!  A systematic way in which to condense extensive data sets into smaller
analyzable units through the creation of categories and concepts derived
from the data
When to code;
!  When testing a hypothesis (deductive), categories and codes can be
developed before data is collected.
!  When generating a theory (inductive), categories and codes are generated
after examining the collected data
Module 11 352
Why Code?
!  It lets you make sense of and analyze your data.
!  For qualitative studies, it can help you generate a general theory.
!  The type of statistical analysis you can use depends on the type of data you
collect, how you collect it, and how it’s coded.
!  Coding facilitates the organization, retrieval, and interpretation of data and
leads to conclusions on the basis of that interpretation
Module 11 353
Levels of Data Coding

!  Open - Break down, compare, and categorize data
!  Axial - Make connections between categories after open coding
!  Selective - Select the core category, relate it to other categories and
confirm and explain those relationships
When to to Develop Codes

!  For surveys or questionnaires, codes are finalized as the questionnaire is
completed
!  For interviews, focus groups, observations, etc. , codes are developed
inductively after data collection and during data analysis
Module 11 354
Data Screening
!  Used to identify miscoded, missing, or messy data
!  Find possible outliers, non-normal distributions, other anomalies in the data
!  Can improve performance of statistical methods
!  Screening should be done with particular analysis methods in mind
Code Book
!  Allows study to be repeated and validated.
!  Makes methods transparent by recording analytical thinking used to devise
codes.
!  Allows comparison with other studies.
Module 11 355
Selecting Codes and Coding Issues

!  Exhaustive – a unique code number has been created for each category
!  Mutually Exclusive – information being coded can only be assigned to one
category
!  Residual other – allows for the participant to provide information that was
not anticipated
!  Missing Data - includes conditions such as “refused,” “not applicable,”
“missing,” “don’t know”
!  Heaping – is the condition when too much data falls into same category
Module 11 356
Descriptive statistics
Descriptive statistics describe the properties of empirical distributions, that is,
distributions of data from samples. There are three areas of interest: the
distribution’s location or central tendency, its dispersion, and its shape
Measures of Location (central tendency)
! Mean
! Median
! Mode
Measures of Variation (dispersion)

! Range - the difference between the largest score and the smallest score
! Interquartile Range - the difference between the 25th and 75th percentiles
! Standard deviation
! Variance
Module 11 357
Measures of Shape
! Skewness - A measure of asymmetry. Zero indicates perfect symmetry; aka
a normal distribution. Positive skewness indicates that the ‘‘tail’’ of the

distribution is more stretched on the side above the mean. Negative
skewness indicates that the tail of the distribution is more stretched on the
side below the mean
Module 11 358
Skewness formula For univariate data Y1, Y2, ..., YN
Where is the mean, s is the standard deviation, and N is the number of

data points
Module 11 359
Measures of Shape
Kurtosis - Is a measure of flatness of the distribution. Heavier tailed
distributions have larger kurtosis measures. The normal distribution has a
kurtosis of 3
Module 11 360
Kurtosis formula For univariate data Y1, Y2, ..., YN
Where is the mean, s is the standard deviation, and N is the number of

data points.
Some sources use excess kurtosis which uses a formula that gives a normal
distribution a value of 0. The formula subtracts 3 from the formula above.
Module 11 361
Frequency Distributions
!  An empirical presentation of a set of observations
!  If it is is ungrouped, it simply shows the observations and the frequency of
each number
!  If it is grouped, then the data are assembled into cells, each cell
representing a subset of the total range of the data
!  The frequency in each cell completes the grouped frequency
distribution.
!  Frequency distributions are often graphically displayed in histograms or
stem-and-leaf plots
Module 11 362
!  Cumulative Frequency Distributions
!  The total frequency distributions up to and including a particular value
!  In the case of grouped data, the cumulative frequency is computed as the
total number of observations up to and including a cell boundary
!  Often displayed as an ogive
Module 11 363
Graphical methods
!  A scatter diagram is a plot of one variable versus another.
! One variable is called the independent variable and it is usually shown on
!  the horizontal (bottom) axis.

! The other variable is called the dependent variable and it is shown on the
vertical (side) axis
Module 11 364
Graphical methods
Scatter diagrams display different patterns that must be interpreted
! 
Strong Positive Strong Negative No Correlation
Module 11 365
Graphical methods
Scatter diagrams display different patterns that must be interpreted
! 
Moderate Positive Moderate Negative Curviliniar
Module 11 366
Scatter diagrams Key Points
!  Be sure that the independent variable, X, is varied over a su⁄ciently large
range. When X is changed only a small amount, you miss a correlation,
even though it really does exist
!  If you make a prediction for Y, for an X value that lies outside of the range
you tested, be advised that the extrapolation is highly questionable
!  Keep an eye out for the effect of variables you didn’t evaluate. It may
either wipe out the effect of your X variable or make you mistake the X
variable you are controlling as the true cause
!  Beware of ‘‘happenstance’’ data
!  If there is more than one possible source for the dependent variable, use
different plotting symbols for each source
Module 11 367
Graphical methods
Normal Probability plots
!  A graphing technique for assessing whether or not a data set is
approximately normally distributed
!  Data is plotted against a theoretical normal distribution in such a way that
the points should form an approximate straight line.
!  Departures from this straight line indicate departures from normality
!  Used to confirm if a normal distribution is a good model for the data
Module 11 368
Graphical methods
Normal Probability plots
Vertical axis: Ordered response values

Horizontal axis: Normal order statistic medians
Module 11 369
Graphical methods
Creating Normal Probability Plots
Observations are plotted as a function of the corresponding normal order
statistic medians which are defined as:
Ni = G(Ui)
Where Ui are the uniform order statistic medians (defined below) and G is the percent
point function (inverse of the cumulative distribution function of the normal distribution
In addition, a straight line can be fit to the points and added as a reference line
Module 11 370
Graphical methods
Histograms
! A pictorial representation of a set of dat.
! Created by grouping the measurements into ‘cells
! Are used to determine the shape of a data set.
! Displays the numbers in a way that makes it easy to see the dispersion and
central tendency and to compare the distribution to requirements

! Excellent troubleshooting tool
Module 11 371
Graphical methods
Creating Histograms
1. Compute range of your data
2. Number of cells determined by sample size
!  100 or less = 7 to 10 cells
!  101-200 = 11 to 15 cells
!  201 or more = 13 to 20 cells
3. Compute width (W) of each cell W = range/# of cells
4. Compute ‘cell boundaries.
5. They have one more decimal place than the raw data values in the data set
6. Low boundary of the first cell is less than the smallest value in the data set
7. Other cell boundaries are found by adding W to the previous boundary
8. Determine into which cell each value falls and tabulate
9. Graph your histogram
Module 11 372
Graphical methods
Example Histogram
Module 11 373
Graphical methods
Histogram Tips
! Can be used to compare a process to requirements if you draw the
specification lines on the histogram

! Always construct a run chart or a control chart as histograms don’t show the
time sequence of the data

! Evaluate the pattern of the histogram to determine if you can detect changes
of any kind. Look for multiple peaks; though small samples often have
multiple peaks that merely represent sampling variation
! Compare histograms from different periods of time
! Stratify the data by plotting separate histograms for different sources of data.
This can sometimes reveal things that even control charts don’t detect
Module 11 374
Graphical methods
Stem-and-Leaf Plots
!  Stem-and-leaf plots are a variation of histograms and are especially useful
for smaller data sets (n<200)

!  A major advantage of stem-and-leaf plots over the histogram, which groups
data in cells, is that the raw data values are preserved as it displays every
piece of data by showing the digits of each number
!  The greatest common place value of the data is used to form stems
!  So the stem Is the digit or digits that remain when the leaf is dropped
!  The numbers in the next greatest place-value position are then used to form
the leaves
!  So the leaf is the last digit on the right side of the number
Module 11 375
Graphical methods
Stem-and-Leaf Plot Example
Module 11 376
Graphical methods
Stem-and-Leaf Plot Tips
!  Always put in a key
!  Always put your data in order
!  To work out the median, you must find the middle value
!  If there are two middle values, you need the average
Module 11 377
Graphical methods
Box-and-Whisker Plots
! Graphically depict groups of numerical data, via the box, through their
quartiles.
! Also have lines extending vertically from the boxes (whiskers) indicating
variability outside the upper and lower quartiles.

! Outliers may be plotted as individual points
Module 11 378
Graphical methods
Box-and-Whisker Plots
!  Use of the box as follows; the bottom and top of the box are always the first
and third quartiles, and the band inside the box is always the second
quartile (the median)
!  The ends of the whiskers can represent several possible alternative values,
the more common being:
!  The minimum and maximum of all of the data
!  One standard deviation above and below the mean of the data
Module 11 379
Graphical methods
Box-and-Whisker Plot Example
Module 11 380
End
!  Types of data and measurement scales
!  Sampling and data collection methods
!  Descriptive statistics
!  Graphical methods
Module 11 381
Module 12 – Measure Phase – Measurement system analysis
(MSA)
Module 12 382
Measurement System Analysis (MSA)
Outline
1. Measurement System Analysis (MSA)
Module 12 383
Measurement system analysis (MSA)
Excessive measurement system variation, increases the risk of:

• Good service being rejected (a cost issue)
• Bad service being accepted (a quality issue)
It is important that we know how much of the measured variation of a process
is due to the variation in the actual process and how much is due to variation
in the measurement system
Overall objective is to reduce error
Module 12 384
MSA can be used to:
!  Compare internal inspection standards with the standards of your customer.
!  Highlight areas where calibration training is required.
!  Provide a method to evaluate inspector training effectiveness as well as
serves as an excellent training tool.

!  Provide a great way to:
!  Compare existing measurement equipment.

!  Qualify new inspection equipment.
Module 12 385
MSA is important to:

!  Study the % of variation in our process that is caused by our measurement
system.
!  Compare measurements between operators.
!  Compare measurements between two (or more) measurement devices.
!  Provide criteria to accept new measurement systems (consider new
equipment).
!  Evaluate a suspect gage.
!  Evaluate a gage before and after repair.
!  Determine true process variation.
!  Evaluate effectiveness of training program
Module 12 386
Error can be partitioned into specific sources:
–  Precision
•  Repeatability - within an operator or piece of equipment
•  Reproducibility - operator to operator or attribute gage to attribute
gage
–  Accuracy
•  Stability - accuracy over time
•  Linearity- accuracy throughout the measurement range
•  Resolution
•  Bias – Off-set from true value
–  Constant Bias
–  Variable Bias – typically seen with electronic equipment,
amount of Bias changes with setting levels
Module 12 387
387
Appropriate Measures are:
!  Sufficient – available to be measured regularly

!  Relevant –help to understand/isolate the problems
!  Representative - of the process across shifts and people
!  Contextual – collected with other relevant information that might explain
process variability
Module 12 388
388
!  The item to be measured can be a physical part, document or a scenario for
customer service.
!  Operator can refer to a person or can be different instruments measuring
the same products.

!  Reference is a standard that is used to calibrate the equipment
!  Procedure is the method used to perform the test
!  Equipment is the device used to measure the produc.
!  Environment is the surroundings where the measures are performed
Module 12 389
Examples of what and when to measure:

!  Primary and secondary metrics
!  Decision points in Process Maps
!  Any and all gauges, measurement devices, instruments, etc
!  X s in the process
!  Prior to Hypothesis Testing
!  Prior to modeling
!  Prior to planning designed experiments
!  Before and after process changes
!  To qualify operators
Module 12 390
390
The Observed variation can be segmented as below
Observed Variation
Unit-to-unit (true) Variation Measurement System Error
Precision Accuracy
Repeatability Reproducibility Stability Bias Linearity
© OpenSource Six Sigma
Module 12 391
391
Gage R+R
!  A precise metric is one that returns the same value of a given attribute
every time
!  Precise data are independent of who estimates them or when the
estimates are made

!  Precision consists of:
!  Repeatability
!  Reproducibility
Together they are know as Gage R+R
Module 12 392
392
Gage R+R
!  Bias is defined as the deviation of the measured value from the actual
value.
!  Stability of a gauge is defined as error (measured in terms of Standard
Deviation) as a function of time.

!  Control Charts are commonly used to track Stability
!  Linearity is the difference in Bias values throughout the measurement
range in which the gauge is intended to be used. This shows the

accuracy of the measurements are through the expected range of the
measurement
!  Formula for Linearity is:
!  Linearity = |Slope| * Process Variation

!  % Linearity = |Slope| * 100
Module 12 393
393
MSA s fall into two categories:
Attribute
!  Pass/Fail
!  Document Preparation
!  Surface imperfections
!  Customer Service Response
Variable
!  Continuous scale
!  Discrete scale
!  Critical dimensions
!  Pull strength
Module 12 394
394
MSA s
! Transactional projects usualy have Attribute based measurement systems

! Manufacturing projects generally use Variable studies, but can use
Attribute studies in some cases
Module 12 395
395
Gage R+R Studies
!  A set of trials conducted to assess the Repeatability and Reproducibility

of the measurement system.
!  Multiple people measure the same characteristic of the same set of
multiple units multiple times (a crossed study)
!  These units are then randomized and a second measure on each unit is
taken
!  Blind studies are the best; with the operators not knowing their measuring
is not part of a test
!  The Analysis of Variance (ANOVA) can also be used to analyze Gage
R&R studies
Module 12 396
396
Gage R+R Study Design Types

•  A Crossed Design is used only in non-destructive testing and assumes that
all the parts can be measured multiple times by either operators or multiple
machines.
–  Gives the ability to separate part-to-part Variation from measurement
system Variation.
–  Assesses Repeatability and Reproducibility.
–  Assesses the interaction between the operator and the part.
Module 12 397
397
Gage R+R Study Design Types
•  A Nested Design is used for destructive testing and situations where it is
not possible to have all operators or machines measure all the parts
multiple times
–  Assumes that all the parts within a single batch are identical enough to
claim they are the same
–  Nested designs are used to test measurement systems where it is not
possible to send operators with parts to different locations
–  Do not include all possible combinations of factors
–  Uses a slightly different mathematical model than the Crossed Design
Module 12 398
398
Gage R+R Studies
!  Estimates for a Gage R&R study are obtained by calculating the variance
components for each term and for error
!  Repeatability, Operator and Operator*Part components are summed to
obtain a total Variability due to the measuring system
!  We use variance components to assess the Variation contributed by each
source of measurement error relative to the total Variation
Module 12 399
399
Gage R+R Study Results
% Tolerance or Study % Contribution Results are

Variance
< =10% < =1% Ideal
10-20% 1-4% Acceptable
20-30% 5-9% Marginal
=>30% =>10 Poor
Module 12 400
400
Conducting a Gage R+R Study
Step 1: Call a team meeting and introduce the concepts of the Gage R&R
Step 2: Select parts for the study across the range of interest
–  If the intent is to evaluate the measurement system throughout the
process range, select parts throughout the range
–  If only a small improvement is being made to the process, the range of
interest is now the improvement range
Step 3: Identify the inspectors or equipment you plan to use for the analysis
–  In the case of inspectors, explain the purpose of the analysis and that
the inspection system is being evaluated not the people
Step 4: Calibrate the gage or gages for the study
–  Remember Linearity, Stability and Bias
Module 12 401
401
Conducting a Gage R+R Study
Step 5: Have the first inspector measure all the samples once in random
order
Step 6: Have the second inspector measure all the samples in random order
–  Continue this process until all the operators have measured all the
parts one time
–  This completes the first replicate
Step 7: Repeat steps 5 and 6 for the required number of replicates
–  Ensure there is always a delay between the first and second inspection
Step 8: Enter the data into Minitab® or other stats package and analyze your
results
Step 9: Analyze results and make necessary changes
Module 12 402
402
Example Gage R+R Study Control Sheet
Module 12 403
403
Gage R+R Study Capability and Acceptability
Module 12 404
404
Gage R+R Study Capability and Acceptability
Module 12 405
405
End
!  Measurement system analysis (MSA)
Module 12 406
Module 13 – Measure Phase – Process and Performance
Capability
Process and Performance Capability
Outline
1. Process capability studies
2. Process capability (Cp, Cpk) and process performance (Pp, Ppk) indices
3. Short-term vs. long-term capability and sigma shift
4. Summary and review of the Measure Phase
Module 13 408
Process capability studies
•  Intended to be regular estimations of a process s ability to meet its
requirements or specifications
•  In other words we are measuring process performance vs.process
specifications
•  Can be conducted on both Discrete and Continuous Data.
•  Most meaningful when conducted on stable, predictable processes
•  Commonly reported as Sigma Level which is optimal (short term)
performance.
Module 13 409
409
•  Intended to be regular estimations of a process s ability to meet its
requirements
•  Can be conducted on both Discrete and Continuous Data.
•  Most meaningful when conducted on stable, predictable processes
•  Commonly reported as Sigma Level which is optimal (short term)
performance.
•  Require a thorough understanding of the following:
–  Customer s or business s specification limits
–  Nature of long-term vs. short-term data
–  Mean and Standard Deviation of the process
–  Assessment of the Normality of the data (Continuous Data only)
–  Procedure for determining Sigma level
Module 13 410
410
Questions to consider:
!  What is the source of the specifications?
!  Customer requirements (VOC)
!  Business requirements (target, benchmark)
!  Compliance requirements (regulations)
!  Design requirements (blueprint, system)
!  Are they current? Likely to change?
!  Are they understood and agreed upon?
!  Operational definitions
!  Deployed to the work force
Module 13 411
411
Process capability (Cp, Cpk) Index
!  Cp is the possible, Cpk is the reality
!  Quantifies the ability of a process to meet the expectations of customers
and other stakeholders.

!  This index usually is converted into a standard deviation or estimate of
defects per million opportunities

!  During Measure Stage, it can create a baseline estimate for a controlled
process
!  During Improve Stage, can confirm process improvements and that the
process is in statistical control

!  During Control Stage, used to monitor processes to confirm that they
remain in a state of statistical control
Module 13 412
Process capability (Cp, Cpk) Index Interpretation
!  Influenced heavily by the distribution assumptions.
!  If the value of Cp (the ratio of tolerance to process variation) is 1, then
tolerance and process variation are equal

!  If the value of Cp is less than one, then the allowable variation is less than
the process variation, which means that the normal amount of variation
could be too much
!  When Cpk is used, it is possible to obtain information about the process
variation and location and their relation to the requirements
Module 13 413
Process capability (Cp) Index formulas
One can replace process standard deviation with sample if process SD

unknown
Where LSL and USL are lower and upper specification limits, respectively.
The percentage of the speciation band used up by the process can be
calculated in the following way:
Module 13 414
Process capability (Cpk) Index formulas
Where
Cpl = (Mean - LSL) /3s
Cpu = (USL - mean) /3s
One can replace process standard deviation and mean with sample SD and
mean if process SD and mean unknown
Module 13 415
Process Performance (Pp, Ppk) Index
!  Pp is the possible, Ppk is the reality
!  A process performance index determines whether a particular batch of
materials will be satisfactory to customers.

!  Its scope is limited to a single batch, which distinguishes it from the process
capability index
!  Used to create process baseline estimates for uncontrolled processes
!  Sample must be large in order to assess any variations in the batch
!  Use when statistical process controls are not possible; because the process
lacks statistical control or because there is insufficient data
Module 13 416
Process Performance (Pp, Ppk) Index Formula
Module 13 417
Process Performance (Pp, Ppk) Index Interpretation
!  Cannot be used to predict future performance

!  Using capability indices generally is better, when a process is in statistical
control
!  If the process performance indices have values less than 1, then tolerance
(variation that can be allowed) is less than the variation in the sample.
!  If the value is 1, then the variation in the sample is exactly the same as the
tolerance.
!  The best result is to have process performance index values of greater than
1, indicating that the sample variation is less than the allowable variation
Module 13 418
Short-term vs. Long-Term Capability and Sigma Shift
! The capability of a process has two distinct but interrelated dimensions.

! First, there is short-term capability, or simply Z.st.
! Second, we have the dimension long-term capability, or just Z.lt.
! Finally, there is the contrast Z.shift = Z.st – Z.lt
Module 13 419
Z.st assesses the ability of a process to repeat (or otherwise replicate) any
given performance condition, at any arbitrary moment in time
The formula is Z.st = |SL – T| / S.st,

Where SL is the specification limit, T is the nominal specification and S.st is
the short-term standard deviation
The short-term standard deviation is S.st = sqrt[SS.w / g(n – 1)]

Where SS.w is the sums-of-squares due to variation occurring within
subgroups, g is the number of subgroups, and n is the number of
observations within a subgroup
Module 13 420
• Z.lt, is intended to show how well the process can replicate a given
performance condition over many cycles of the process
• In its purest form, Z.lt is intended to capture and “pool” all of the observed
instantaneous effects as well as the longitudinal influences
Module 13 421
The formula is Z.lt = |SL – M| / S.lt,

Where SL is the specification limit, M is the mean (average) and S.lt is the
long-term standard deviation
The long-term standard deviation is given as S.lt = sqrt[SS.t / (ng – 1)],

Where SS.t is the total sums-of-squares
In this context, SS.t captures two sources of variation – errors that occur
within subgroups (SS.w) as well as those that are created between
subgroups (SS.b). Given the absence of covariance, we are able to compute
the quantity SS.t = SS.b + SS.w
Module 13 422
Sigma Shift
!  Processes usually do not perform as well in the long term as they do in the
short term.
!  Thus the number of sigmas that will fit between the process mean and the
nearest specification limit will likely drop over time.
!  To account for this real-life increase in process variation over time, an
empirically-based 1.5 sigma shift is introduced into the calculations
!  So a process that fits 6 sigma between the process mean and the nearest
specification limit in a short-term study will in the long term fit only 4.5 sigma
!  Therefor the 3.4 DPMO of a six sigma process in fact corresponds to 4.5
sigma, namely 6 sigma minus the 1.5-sigma shift introduced to account for
long-term variation
Module 13 423
End
In this Module we have covered
!  Process capability studies
!  Process capability (Cp, Cpk) and process performance (Pp, Ppk) indices
!  Short-term vs. long-term capability and sigma shift
WE WILL NOW DO A QUICK REVIEW OF THE MEASURE PHASE
Module 13 424
Measure Phase – Summary
!  Tie back all activities to the CTQ list
!  Validate that you CTQ operational definition is the same as the customer's
!  Detail out the process map
!  Define your defect, target performance and limits
!  Identify the data to be collected
!  Create a data collection plan
!  Make sure your have a reliable measurement systems in place
Measure Phase Summary &

Review Questions
Measure Phase – Summary
Questions to ask at phase end
!  Which processes are we targeting?
!  Can we address the problem with a single project?
!  Our our measurements continuous and show us the true variation?
!  Will our measurements reflect the customer's view of a single transaction?
!  Where can our measurement fail or be manipulated?

Review Questions
Measure Phase – Review Questions
Measure Phase Review Question #1
When a GreenBelt is developing a Process Map to define a complex process
he will frequently include activities across various department to capture all
the appropriate activity. He will use _____________ to show which
department is responsible for which steps in the process
a. Subscripts
b. Superscripts
c. Swim Lanes
d. Fence Posts

Review Questions
This formula is used to calculate a Z score that, with the
appropriate table, can tell you what
____________________________________.
a. Ratio the area under the curve is to the total population

b. Number of Standard Deviations are between X and µ
c. The Median of the sample population is
d. Proportion of the data is between X and µ

Review Questions
As we calibrate our Measurement System to assure accurate data we
frequently encounter Bias which is the __________________ of a measured
value from the ________________ value
a. Spread, Mean of the population

b. Deviation, hoped for
c. Deviation, true
d. Spread, idea

Review Questions
Measure Phase Review Question Answers
1. C Swim Lanes
2. D Proportion of the data is between X and µ
3. C Deviation, true

Review Questions
Module 14 – Analyze Phase – Exploratory Data Analysis &
Hypothesis Testing
Module 14 – Analyze Phase –
Exploratory Data Analysis & Hypothesis Testing
Outline
1. Analyze Phase Overview
2. Multi-Vari studies
3. Correlation and Linear Regression
4. Basics of Hypothesis Testing
5. ANOVA
Module 14 432
Analyze Phase Overview
!  The team will focus on analyzing the sources of variation in the target
process
!  Based on the high-level problem, the tools to drill down with will be selected
!  This analysis may require the use of sophisticated statistical tools
!  The team will analyze the value stream. The value stream is the set of
activities that create value for the customer
!  The team will also identify the process drivers, which are the activities that
exert a significant influence on the results of processes
Module 14 433
Analyze Phase Overview
Pick the tools
!  Cycle Time Reduction
–  Value Stream Analysis

–  Velocity, Space & Movement, etc.
!  Variation Reduction
–  Hypothesis Testing
–  Correlation
Module 14 434
Hypothesis Testing
Hypothesis Testing
!  Integrates the Voice of the Process (VOP) with the Voice of the Business
(VOB) to make data-based decisions to resolve problems
!  The VOP describes what the process is telling us. What it is capable of
achieving, whether it is under control and what significance to attach to
individual measurements
!  The VOB describes the stated and unstated requirements of the business
Module 15 435
Hypothesis Testing
Hypothesis Testing
!  Can help avoid high costs of experimental efforts by using existing data
!  Can help establish a statistical difference between factors from different
distributions; such as from different shifts or suppliers
!  Two types of significant differences occur and must be well understood,
practical and statistical
!  Failure to tie these two differences together is one of the most common
errors in statistics
Module 15 436
Hypothesis Testing
Hypothesis Testing
Practical Difference: The difference which results in an improvement of

practical or economic value to the company. Reflects the VOB
Statistical Difference: A difference or change to the process that probably

(with some defined degree of confidence) did not happen by chance. Reflects
the VOC
Module 15 437
Hypothesis Testing
Hypothesis Testing
!  The practical difference to be achieved must match the statistical
difference.
!  Which can be either a change in the Mean or in the variance.
!  Detection of the difference is then accomplished using Hypothesis Testing
!  A Hypothesis Test converts the practical problem into a statistical problem.
!  Since small sample sizes are used to estimate population parameters, there
is always a chance of collecting a non-representative sample

!  Inferential statistics allows us to estimate the probability of getting a non-
representative sample
Module 15 438
Hypothesis Testing
Basics of Hypothesis Testing
! Hypothesis testing establishes a degree of confidence and then compares a

sample statistic against a historical value or another sample statistic
! Useful for distinguishing the factors that contribute to variation in data.
! Primarily, this type of testing is used during designed experiments and
regression analysis
! In the improve stage, its primary function is comparing the averages of
improved processes with baseline estimates

! In order to perform hypothesis testing, the population must be assumed
constant and homogenous.

! Also, that samples are random and representative must be assumed
Module 15 439
Hypothesis Testing
Steps in Hypothesis Testing
1. The first step in hypothesis testing is stating the null hypothesis, H0. In most
cases, the null hypothesis represents the value that the test aspires to prove
2. The next step in hypothesis testing is defining the alternative hypothesis
(H1). The alternative hypothesis should cover all of the area excluded from
the null hypothesis
3. The third step is either setting a value for p or selecting a significance level
(α)
Module 15 440
Hypothesis Testing
Steps in Hypothesis Testing
4. The significance level is the chance of incorrectly rejecting a true hypothesis

in what is known as a Type 1 error
5. It is considered better to set a p value because this allows more freedom for
adjustment later in the experiment
6. Next, samples are collected and statistics are calculated.
7. The final step in hypothesis testing is drawing a conclusion
Module 15 441
Hypothesis Testing
Hypothesis Testing Interpretation
If the calculated statistic is larger than the critical value of the test statistic for
the given level of significance, then the null hypothesis must be rejected
If the critical value of the test statistic is larger, then the null hypothesis is
accepted
Software programs such as Excel or Minitab can use the calculated p value to
indicate whether the obtained results are appropriate, assuming that the null
hypothesis is true
Module 15 442
Hypothesis Testing
Hypothesis Testing Interpretation
! If the p value is small, then the chances of obtaining results similar to those
gathered during the experiment are so small that the null hypothesis should
be rejected
! If the null hypothesis is not rejected in that case, then the experiment is said
to have reached a weak conclusion, because the means may or may not be
equal
! When the null hypothesis is confirmed, however, the experiment is said to
have produced a strong conclusion
Module 15 443
Hypothesis Testing
Type I errors.
! A type I error, also known as an error of the first kind, occurs when the null
hypothesis(H0) is true, but is rejected

! The rate of the type I error is called the size of the test and denoted by the
Greek letter α (alpha).

! It usually equals the significance level of a test.
! In the case of a simple null hypothesis α is the probability of a type I error.
! If the null hypothesis is composite, α is the maximum (supremum) of the
possible probabilities of a type I error.
Module 15 444
Hypothesis Testing
Type II errors.
! A type II error, also known as an error of the second kind, occurs when the
null hypothesis is false, but erroneously fails to be rejected

! The rate of the type II error is denoted by the Greek letter β (beta) and
related to the power of a test (which equals 1−β)

! Hence it is also known as Beta Risk
Module 15 445
Hypothesis Testing
Nonparametric Tests
! Are occasionally used in place of traditional hypothesis tests for the equality
of two means
! These tests are more effective when the assumptions associated with
common statistical distributions cannot be met

! In the analyze stage, nonparametric tests are used to compare the means
from samples with different conditions

! In the improve stage, they are used to assess whether process averages
have been improved over baseline estimates after the implementation of

changes
! These tests do not require statistical normality or any other quality in order to
be valid
! One disadvantage of this form of testing is its requirement of a larger sample
size
Module 15 446
Hypothesis Testing
Creating Nonparametric Tests
! For a nonparametric test on the equality of means, the null hypothesis H0

will be that population 1’s median is equal to population 2’s median.
! The alternative hypothesis H1, then, is that population 1’s median does not
equal population 2’s median

! Median is preferable to mean in these tests because it indicates central
tendency regardless of distribution

! The next step in the test involves declaring a significance level or p value.
After samples have been collected, the probability of Type II error can be
assessed
Module 15 447
Hypothesis Testing
Interpreting Nonparametric Tests
! The null hypothesis is rejected if the calculated statistic is greater than the
critical value of the test statistic.
! If the calculated statistic does not exceed the critical value of the test
statistic, then the null hypothesis is accepted
Module 15 448
Exploratory Data Analysis
Multi-Vari plots
! Are effective tools for assessing the variation within samples or within
particular parts.
! Multi-Vari plots can be used to analyze variation over time or between
different batches
! Primarily used to isolate the causes of variation and to obtain more
information about the interactions among factors

! Identifies possible X s or families of variation. These families of variation can
hide within a subgroup, between subgroups or over time

! Helps screen X s by visualizing three primary sources of variation. Later we
will perform Hypothesis Tests based on the findings
Module 14 449
Multi-Vari plots
! The first step in constructing a Multi-Vari plot is determining the system for
gathering data.
! This data should then be placed on a plot, with each sample unit represented
by a different symbol.
! The length of each symbol will indicate the variation within the sample
! However, it will not indicate whether the process is unstable from a statistical
perspective
Module 14 450
Multi-Vari plot example
© Minitab
Module 14 451
Sources of Variation
Within Unit or Positional
–  Within piece variation related to the geometry of the part.
–  Variation across a single unit containing many individual parts such
as a wafer containing many computer processors.
–  Location in a batch process such as plating.
Between Unit or Cyclical

–  Variation among consecutive pieces.
–  Variation among groups of pieces.
•  Variation among consecutive batches.
Temporal or over Shift-to-Shift

–  Day-to-Day
–  Week-to-Week
Module 14 452
452
Conducting a Multi-Vari study
1. Ascertain the historical level of problem variation in the process
2. Define the study unit
3. Collect data from the process
4. Create the Multi-Vari plot by plotting the data in the positional, cyclical, and
temporal groups
5. Interpret the Multi-Vari plot by reviewing the magnitudes of each of the
categories of variation — positional, cyclical, and temporal
© Minitab
Module 14 453
Correlation and Linear Regression
! Correlation analysis is the study of the strength of the linear relationships

among variables)
! Regression analysis is the modeling the relationship between one or more
independent variables and a dependent variable

! A regression problem considers the frequency distributions of one variable
when another is held fixed at each of several levels.

! A correlation problem considers the joint variation of two variables, neither of
which is restricted
! Correlation and regression analyses are designed to assist in studying cause
and effect
! We have already touched on the basics when we looked at scatterplots
Module 14 454
! When conducting regression and correlation analysis we can distinguish two

main types of variables:
!  Predictor variables or independent variables
!  Response variables or dependent variables.
! As a result of changes that are made, or take place in the predictor
variables, an effect is transmitted to the response variables

! We hope that a small number of predictor variables will ‘explain’ nearly all of
the variation in the response variables

! In practice, it can be difficult to draw a clear distinction between independent
and dependent variables; also both can be responding to an unknown

variable (e.g. ice cream sales and crime rates)
Module 14 455
! Also important to studying cause and effect is that of the data space of the
study
! The data space of a study refers to the region bounded by the range of the
independent variables under study

! Defining the data space can be quite difficult when large numbers of
independent variables are involved
Module 14 456
Things to watch out for
!  Non-linear relationships will be missed so always create a scatter-plot

!  Be careful what you compare. Some x-y correlations make no sense. These
are termed chance or nonsense correlations
!  This can happen if we do not think through the problem and/of fail to
uncover a third variable
!  Is our Y really our X or vs versa
!  Relationships can be dynamic
Module 14 457
Things to watch out for
And finally...
CORRELATION DOES NOT NECESSARY MEAN CAUSATION...
Module 14 458
! Autocorrelation charts, otherwise known as the autocorrelation function

(ACF), are used to determine the degree to which current data depends on
previously gathered data
! This is accomplished by automatically examining multiple observations of a
particular variable with an eye toward possible correlations over time

! They are similar to the scatter diagram, except the latter identifies
correlations between different characteristics
Module 14 459
Autocorrelation charts
! In the Measure Phase, these charts may be used to gather information about
processes, including their effects on baseline data
! In the Analyze stage, autocorrelation charts are used to investigate the
regression residuals, namely to test for independence

! Control stage, autocorrelation charts are used to develop a strategy that
takes into account a process' serial dependence
Module 14 460
Creating Autocorrelation charts
! First step of the autocorrelation function is testing for autocorrelations

between each of the isolated observations
! Each step will be considered in relation to the steps immediately before and
after it. This consideration is called the lag 1 autocorrelation

! There also will be autocorrelations for distances. For example, the lag 3
autocorrelation will consider the relations between the first and fourth
observations, second and fifth observations, and so on
Module 14 461
Creating Autocorrelation charts
! The general recommendation suggests testing for autocorrelations from lag

1 to lag n/4, where n is the total number of observations
! When used to detect non-randomness, it is usually only the first (lag 1) that
is of interest
! When used to identify an appropriate time series model, the autocorrelations
are usually plotted for many lags
Module 14 462
Autocorrelation Function Formula
Given measurements, Y1, Y2, ..., YN at time X1, X2, ..., XN, the lag k
autocorrelation function is defined as
Although the time variable, X, is not used in the formula for autocorrelation,
the assumption is that the observations are equi-spaced
Module 14 463
Autocorrelation Interpretation
! When interpreting an autocorrelation chart, one should be aware of

phenomena that might produce false correlation
! Sometimes autocorrelation will be significant only at adjacent data points,
where the lag is very low. To diminish this autocorrelation, one should
increase the time between data point collection
! Another source of false correlation emerges with sampling from several
different streams in a process. Sometimes large autocorrelations for smaller

lags can influence larger lags
Module 14 464
Linear Regression
!  Regression analysis is a system for identifying when independent variables

are influenced by one or more dependent variables
!  In the Measure Phase, regression analysis is used to evaluate the degree
to which a measurement system is linear
!  In the Analyze Phase, regression analysis can be used to explore the
connections between metrics and process factors
!  In the improve stage, regression analysis is useful for confirming these
connections after improvements have been implemented
Module 14 465
Linear Regression
!  A simple linear regression tries to orient data points around a single straight
line
!  In Six Sigma the formula expressed as this:
!  Where β0 is the estimation of the intercept and β1 is the regression line’s

slope. The values for intercept and slope typically are estimated according
to the method of least squares, in which the line is drawn with a minimal
squared distance to each data point.
!  The statistical equation for a simple linear regression includes the word
error as an acknowledgement that every set of data points will have some
inaccuracies
Module 14 466
First-order model of multiple regression
! If more than one factor influences a dependent variable multiple
regression must be used
! Multiple regression takes into account the interactions between these
multiple factors
! In a first-order model, the value of the dependent variable is based on the
influence of each factor by itself, as well as each possible combination of
two factors
! Whatever error exists in the model is assumed to be the same for all
factors and combinations of factors
Module 14 467
First-order model of multiple regression
! A first-order multiple regression usually will produce an essentially straight
line over small regions, so it can be useful when only targeted data is
needed
! Examined from a more distant perspective, the model will appear as a
linear regression for which the plane has been curved or twisted.
! This flexing of the plane is caused by the influence of interacting factors
Module 14 468
Example multiple regression plot
Module 14 469
Higher-order models of multiple regression
! When more complex analysis is required for a process in which more than
one factor influences a dependent variable, a higher-order model of
multiple regression must be performed
! A higher-order multiple regression can include squares and cubes of the
values, which will produce a response surface with definable peaks and
valleys
! Is valuable only if exhaustive experiments already have been performed
on the main effects
Module 14 470
Higher-order models of multiple regression
! Useful for mapping smaller regions, in particular peaks, valleys, and
minimaxes (intersections between the minimum for one factor and the
maximum for another).
! Also are good at defining the area that surrounds a stationary point
! In Six Sigma, these models often are used to evaluate how current
operating parameters influence the response
Module 14 471
Residuals analysis
! Residuals are the differences between a response’s observed value and a
regression model’s predicted value for that response
! A residuals analysis of a regression model will reveal any unusual
patterns that could suggest error in the model.
! Statistical software programs will calculate a standardized residual such
that the variance is set to 1. This makes outliers more obvious
Module 14 472
Residuals analysis
! The most common technique of residuals analysis is the normality test, in
which the randomness of error is tested by creating a distribution of the
residuals
! If the error truly is random, then the residuals should follow a normal
distribution with a mean of zero
! Residuals also can be used on a scatter diagram to assess the
independence of a variable
Module 14 473
Hypothesis Testing
Analysis of Variance (ANOVA)
An analysis of variance (ANOVA) is a table that depicts;

! 
!  The sum-of-squares variance that can be credited to a particular

source
!  The sum of the squares that can be credited to error
!  The total sum of squares from the data
This table includes F statistics related to the significance of the source
! 
relative to the error
Module 15 474
Hypothesis Testing
! Analysis of variance is used to identify the origins of errors in measurement

! This analysis is useful especially for processes that damage or diminish the
resources involved, such that a repeatability and reproducibility (R & R) is not

possible
! It is also used to gather information about the statistical significance of a
regression models
! ANOVA is often used in this manner to pinpoint possible process drivers.
! Another use of ANOVA in the Analyze Phase is to identify differences
between data subsets in order to identify the causes of variation within a

process
Module 15 475
Hypothesis Testing
! In ANOVA variation within each subgroup is compared to the variation found
between different subgroups.
! The variation within each subgroup is found by sampling from the subgroup
repeatedly.
! The variation between different subgroups is found by analyzing the
essential differences between the averages of each subgroup.

! ANOVA begins with the null hypothesis, that all subgroup averages are equal
Module 15 476
Hypothesis Testing
! Then, the F statistic is used to compare the average variation between

subsets, known as the mean square treatment, with the sun of the squares of
the residuals, known as the mean square error
! An F test assumes that subsets have a normal distribution and equal
variance
! If the p value for the F test is less than 0.05, then the null hypothesis can be
rejected. This suggests that one or more of the subset averages is different
Module 15 477
Hypothesis Testing
Example Analysis of Variance (ANOVA)
Module 15 478
End
!  Analyze Phase Overview
!  Multi-Vari studies
!  Correlation and Linear Regression
!  Basics of Hypotheses Testing
!  ANOVA
Module 14 479
Module 15 – Analyze Phase – Process Drivers
Module 15 480
Process Drivers
Outline
1. Value Stream
2. Batching
3. Lean Metric Velocity
4. Setup Time
5. Reducing Movement and Physical Space
6. Analyze phase summary and review
Module 15 481
Process Drivers
Value Stream Mapping;
! A communication tool that depicts the flow of materials and
information through an organization or series of processes related to

the production of goods or services
Used to identify waste and redundancy in processes
! 
!  Will document both the current state and the future state
The current state value map is examined for steps that do not add
! 
value. These non-value-added steps need to be eliminated or

minimized
Module 15 482
Process Drivers
! The future state map depicts the process after planned
improvements have been implemented. Ideally it will be less

complicated than the current state, with a significant reduction in
non-value-added activities
Each activity in a process is represented on the map.
! 
Each activity is accompanied by information on: cycle time, down

! 
time, in-process inventory, path of information, and path of materials
Module 15 483
Process Drivers
!  Value-adding steps should be separated from the the non-value-
adding steps in a way that makes them stand out

!  This separation into the value stream and the 'waste' steps,
focuses ones attention on what is value-adding and what isn't

!  The value stream is the process and the non-value streams the
operations
Module 15 484
Process Drivers
!  Document customer demand
!  Define processes using operational data
!  Show material flow
!  Show information flow
!  Compute lead times (value adding time)
Module 15 485
Process Drivers
Key Value Stream Mapping terms;
! Lead Time - The average time it takes for one unit to go through the
entire process including time waiting between sub-processes (aka

throughput time or turnaround time
!  Lead Time = Cycle Time x units of WIP x number of
operations + queue time between processes

! Order Lead Time – The time it take from when the customer orders
the product or service to when they receive it

! Queue Time - The time between sub-processes that the item gets
moved or sits around waiting for someone to work on it (aka Waiting

and Transportation Time or Inventory/Transportation Time)
Module 15 486
Process Drivers
!  Process Time - The time that the item is being worked on by an
Operator (aka Touch Time). Focus is Operator time expended

!  Processing Time = manual Work + Walking + Waiting
!  Value Add Time - Time for those process steps that actually value
to the item (aka Value Creating Time)

!  Machine Time - The time that a machine is working on the item, will
include waiting for a process to complete; such as glue to set

!  Process Lead Time = The time that the item or batch of items is
being worked on before it can be passed on to the next process

!  Process Lead Time = Processing Time * Batch Size
Module 15 487
Process Drivers
! Cycle Time (CT) - The average time between completed units
coming out the end of the process

!  Cycle Time = Processing Time / # of Operators
! Machine Cycle Time - The average time between completed units
coming out of a machine

! Work Time Available – Actual work time after breaks, meeting, shift
setup and cleanup, and other planned non-working time is deducted

! Takt Time – your customer-driven cadence or drumbeat
!  Takt Time = Total Working Time Available / Target Units to
Produce
Module 15 488
Process Drivers
! Target Cycle Time = Operational Takt Time adjusted for other
factors, such as seasonal demand

! Change Over Time (CO) – time needed to set up for a new batch
! Pitch - how often work is released and monitored
! Pitch = takt time * pitch batch size (the batch size released to the
pacesetter process)
! Change Over Batch Size - how many items get processed before a
Change Over is needed.

! Out of Cycle Work – mid-shift tasks that are not performed in every
cycle, but reduce time available to meet Takt Time, such as

palletizing, mid-shift inspections, etc
Module 15 489
Process Drivers
! Kanban – signaling device to authorize the release of work
! Supermarket – a place where a standard amount of inventory is
stored in order to ensure uninterrupted supply to a downstream

process
! Bursts – signify where a Kaizen event is or will occur
Module 15 490
Process Drivers
Process data boxes should contain;
! Cycle time (CT): Observed & Effective
! Changeover time (CO) & frequency
! % Availability to Demand
! Number of operators
! % Quality level (first-pass yield)
! Batch size
Module 15 491
Process Drivers
Creating a Value Stream Map
1. Draw customer icon
2. Draw the outbound shipping icon and note the delivery frequency
3. Draw supplier icon
4. Draw the inbound shipping icon and note the delivery frequency
5. Add process boxes in left to right sequence. Add data boxes below
the process box
6. Add communication arrows. Note methods and frequencies
7. Gather process attributes and add to data boxes
8. Add operator symbols
Module 15 492
Process Drivers
9. Add inventory locations and levels in days of demand
10. Graph at bottom
11. Add push, pull, and FIFO icons
12. Add working hours
13. Add cycle and lead times
14. Calculate total cycle and lead times
15. Add other relevant information
Module 15 493
Process Drivers
!  Cycle Time and Takt Time should be measured in seconds per unit
!  Work Time Available should be measured in minutes per day
!  Best to deduct foreseeable Out of Cycle Work from the Work Time
Available prior to calculating Takt Time
Module 15 494
Process Drivers
!  If the map contains an overwhelming number of flow interruptions,
then it is advisable to combine Process Boxes

!  Don't worry too much about capturing every detail in an As Is VSM,
because it will change

!  Do identify shared processes (used by two or more value streams).
These are referred to as monuments.

!  Do identify iterative processes
Module 15 495
Process Drivers
Capturing Information
Time it;
!  Cycle Time (CT) - Time for one part. Time before repeating
operation
!  Change over time (CO) - Time to switch product type
Module 15 496
Process Drivers
Measure or count;
!  Travel (TR) - How far does the Operator travel to do their job?
!  Inventory (I) - Count the amount of inventory before and after the
process
Module 15 497
Process Drivers
Observe;
!  Yield (Y) - % How many pass inspection
!  Up Time (UP) - % machine is up and running
!  Scheduled Changes (SC) -Number of scheduled changes per
week
!  Waiting time (WT) - Find how often Operators are waiting for
something to do. How often are they waiting for another operation
to be done
Module 15 498
Process Drivers
Ask;
!  Correct Information (CI) - % of times the job instructions are correct
and accurate. How many times do Operators ask for clarification

!  Operators per shift (OPS)
!  Production Scheduling (PS)
!  Inventory Flow up (IFU) - Where does inventory come from, all
sources
!  Inventory Flow down (IFD) - Where does inventory go to, all places
Module 15 499
Process Drivers
Tips;
! Focus on a product family within single plant
! Get leadership approval and buy-in
! Conduct door-to-door process walk
! Encourage participation of all stakeholders
! Use pencil and paper to start
! Use your As Is process map as a starting point in your
understanding of the value stream
Module 15 500
Process Drivers
Tips;
!  Communicate to all areas before your visit
!  Introduce yourself and explain your purpose
!  Remember, the workers are the experts for their tasks!
!  Respect people and their work space
Module 15 501
Process Drivers
Value Stream Map Symbols – Note there is a lot of variation in these symbols;
Module 15 © Flylib.com 502*

Process Drivers
Sample Value Stream Map;
© Wikipedia
Module 15 503
Process Drivers
!  Look for non-value-adding steps that are preparing for, or tidying

up for the value-adding step and are closely associated with work-
station or operator
!  Look for steps that are related to transportation, approvals, logging,
or other ancillary activities
!  Key metrics associated with value stream mapping are value
adding times and non-value adding times
!  Always true that Lead Time >= Processing Time >= Value Add
Time
Module 15 504
Process Drivers
Batching
! A traditional method of reducing waste
! When work is batched a large number of essentially identical tasks are
gather and performed the same time

! When tasks are divided into batches, the time required to perform them
clearly is shorter
! However, batching creates delays at the beginning and end of the activity
! The team must wait for a number of tasks to arrive in the input queue before
beginning, creating unnecessary lag time

! Also the entire batch does not move on to the next step of the process until
every item has been subjected to the batched step

! This wait is one of the greatest contributors to lead time
Module 15 505
Process Drivers
Batching
! However, there are times when batching makes sense
! For example, if the set up time for the equipment is significant then
performing the activity in batches may be more efficient

! When the cost of moving materials is large is another instance when
batching makes sense
Module 15 506
Process Drivers
Lean Metric Velocity
! Velocity, in Lean, is a metric that indicates the rate at which value is added
during a process phase

! The calculation of the lean metric velocity is used to help rank cycle time
improvement opportunities in order of importance as well as aid us in our

analysis of the the value stream
! The basic formula for the calculation of Velocity is:
!  number of value-added steps / process lead time.

! Process lead time is calculated according to Little’s law:
!  number of items in the process /number of times the process is

completed every hour
Initiating a process observation log should be done before attempting to
! 
calculate velocity
Module 15 507
Process Drivers
Calculating Process Velocity
!  Categorize each task as value-added, non-value-added but necessary
(NVA type 1), or non-value-added and unnecessary (NVA type 2)

! Measure the process time for each task regardless of its value
! Measure the inspection time
! Measure move or transportation time
! Measure the queue time
Throughput Time = Process time + Inspection time + Move time + Queue time
Then add the times for each value-added task
! 
Process Velocity=Total throughput time/value-added time
Module 15 508
Process Drivers
Using Process Velocity
! Velocity indicates the degree to which a process responds to customer
demands
! If there is less work in progress, lead times are shorter and velocity is greater
!  If the lead times are longer, then velocity is slower
! When velocity is slow, the business cannot respond quickly to new orders
from customers
! Looking at the various factors will point you in the best direction for making
improvements
Module 15 509
Process Drivers
Setup Time
! Setup time is the interval between the completion of the last item and the
beginning of the next item

! Consists of four components:
!  Preparation - the set of tasks necessary to gather all of the

materials and people for the activity
!  Replacement - the set of tasks required to adjust and reconfigure
equipment before the next item can be processed
!  Location - the positioning or moving tasks that must be completed
between iterations of a process
!  Adjustment - the set of monitoring or fine-tuning tasks that must
be performed between iterations to ensure correct performance of
a process
Module 15 510
Process Drivers
Setup Time
! Preparation time is considered a non-value-added activity
! Reduce preparation time by:
!  Staging supplies and equipment as close as possible to the

workstation
!  Group employees in work cells so the entire operation can be
completed without moving the work-in-progress
!  Leave equipment on and ready to go even when not in use
Module 15 511
Process Drivers
Setup Time
! Replacing and relocating equipment and resources prior to a process is
anon-value-added activity
! Reduce replacement and relocating time by:
!  Standardizing setups
!  Simplifying the setup protocol
Module 15 512
Process Drivers
Setup Time
! Adjustments prior to a process is a non-value-added activity
! Reduce adjustment time by:
!  Establishing good process controls

!  Ensuring that the process components being targeted are on the
critical path is essential, otherwise you are wasting your time
Module 15 513
Process Drivers
SMED (Single Minute Exchange of Dies)
For many people, changing a single tire can easily take 15 minutes.
For a NASCAR pit crew, changing four tires takes less than 15 second
WHY IS THAT?
Module 15 514
Process Drivers
Some of the techniques used by NASCAR pit crews such as;

!  Performing as many steps as possible before the pit stop begins
!  Using a coordinated team to perform multiple steps in parallel
!  creating a standardized and highly optimized process
Are also used in SMED
Module 15 515
Process Drivers
!  Goal is rapid changeover from producing item or batch A, to item or batch B
!  Not just for shop floors
!  Don't take the single minute literally
!  Key is to cut-out wasted effort and activities as we as streamline the setup
process
!  Activities divided into two categories;
–  Internal – Those activities that can only be completed when the

machine or process in question is not running
–  External – Those activities that can be done while the machine or
process is running
Module 15 516
Process Drivers
!  Start by collecting two weeks of data in order to determine where productive
time is being lost. It may be that there are more critical areas to address
than setup time (SMED)
!  If changeover setup time constitutes 20% or more of the lost time, then
SMED is worth the effort

!  Set up a pilot
!  When possible convert Internal activities into External activities
!  Staging, reordering steps division of labor, etc.
!  Make the remaining internal activities flow. Optimize
!  Reordering steps, eliminating steps, etc.
!  Optimize scheduling
Module 15 517
Process Drivers
!  Start by collecting two weeks of data in order to determine where productive
time is being lost. It may be that there are more critical areas to address
than setup time (SMED)
!  If changeover setup time constitutes 20% or more of the lost time, then
SMED is worth the effort

!  Set up a pilot
Module 15 518
Process Drivers
A good pilot is when;
! Changeover has significant room for improvement, but not overwhelming in
scope
! Has a large variation in changeover times
! Multiple weekly changeovers, so the changes can be quickly tested
! Buy in from the employees familiar with the equipment
! The machine is a constraint/bottleneck; thus improvements will bring
immediate benefits – do minimize downtime risk by building temporary stock

of its output
Module 15 519
Process Drivers
1. Record a baseline on the pilot machine
2. Identify each element of the changeover, and whether its internal (machine
needs to be off) or external (can be done if the machine is on)
3. Only observe
4. Separate external elements This can often cut set up times in half
5. Convert internal elements into external elements if at all possible – do think
outside the box. eg.
!  Prepare parts in advance, such as preheating
!  Use duplicate pre-aligned jigs and simply drop in the duplicate on
changeover
!  Modularize equipment
!  Modify equipment, such as adding a guard to enable safe cleaning
while running
Module 15 520
Process Drivers
6. Streamline remaining elements

!  Eliminate bolts
!  Eliminate adjustments
!  Eliminate motion
!  Eliminate waiting
!  Standardize hardware
!  Create parallel operations
Module 15 521
Process Drivers
Reducing Movement and Physical Space
! The Analysis phase often reveals that much time is lost simply moving from
one work site to another

! One of the most effective strategy for reducing cycle time often involves
consolidating the area in which a task is performed

! Another approach to reducing wasteful movement requires grouping
employees in multi-function teams rather than single-function departments

! A key tool for performing movement analysis is the Spaghetti diagram
Module 15 522
Process Drivers
Spaghetti Diagram;
! Used to track motion of a person, item, or activity related to a process via
continuous flow lines

! Identifies redundancies in the work flow and opportunities to expedite
process flow
! Also highlights major intersection points; these point are causes of delay
! Helps one see waste that would be otherwise overlooked.
! Like Value Stream maps, one can create current state and future state
diagrams
Module 15 523
Process Drivers
Spaghetti Diagram example – As Is and To Be
Module 15 524
End
Process Drivers
!  Value Stream
!  Batching
!  Lean Metric Velocity
!  Setup Time
!  Reducing Movement and Physical Space
WE WILL NOW HAVE A SHORT REVIEW OF THE ANALYSE PHASE
Module 15 525
Analyze Phase – Summary
!  Develop graphical representations of data to detect pattern
!  Define and calculate a z score or DPMO
!  Identify a list of potential Xs
!  Do statistical testing on population differences
!  Analyze the value stream
!  Produce a short list of critical factors that need to be improved
Analyze Phase Summary &

Review Questions
Analyze Phase – Summary
Questions to ask at the end of the phase:
!  What is the current process's capability?
!  Is the process statistically stable?
!  Is the data discrete of continuous?
!  What does the distribution look like?
!  Have we been able to short-list the potential Xs?
!  What is the null hypothesis, and what is the alternate hypothesis?
!  Which one is in play?
!  Is the required improvements feasible?

Review Questions
Analyze Phase – Review Questions
Analyze Phase Review Question 1
In an “X” Sifting exercises a GreenBelt will use a(n) _______________ to
assist in isolating families of variation that may exist within a subgroup,
between subgroups or vary over time.
a. Multi-Vari Chart
b. Pareto Chart
c. FMEA
d. Shewhart Analysis

Review Questions
Analyze Phase Review Question #1 Answer
1. A Multi-Vari Chart

Review Questions
When analyzing sample data one may experience a Bimodal Distribution with
each mode displaying Normal Distribution. This could be caused by
__________________________ .
a. Two different machines being read

b. Two operators on different shifts
c. Two suppliers parts being used
d. All these are correct answers

Review Questions
2. D All these are correct answers

Review Questions
A manufacturer was considering changing suppliers for a particular part. The
requirement is that the average cost of the part be less than or equal to $32 in
order to stay within budget. A sample of the 32 initial deliveries had a Mean of
the new product upgrade price of $28 with an estimated Standard Deviation
of $3. Based on the data provided, the Z value for the data assuming a
Normal Distribution is?
a. 0.67
b. 1.33
c. 2.67
d. 4.33
Review Questions
3. B 1.33

Review Questions
Module 16 – Improve Phase – Design of Experiments (DOE)
Module 16 – Improve Phase –
Design of Experiments (DOE)
Outline
1. Improve Phase Overview
2. Basic DOE terms and Designs
3.  DOE Graphs and Plots
Module 16
Improve Phase Overview
!  The first major objective of the Improve phase is to set the new process
operating conditions. These conditions are based on the experimentation
and analysis of the measure and analyze phases.
!  The next objective of the improve stage is to identify and address the failure
modes for the new processes
!  Assessing and predicting the benefits of the proposed solution also is
appropriate. Before making massive changes, the team should be able to
guess how positive the results of these solutions will be
!  The final objective of the improve stage is to implement and confirm
process improvements
Module 16
Design of Experiments
! An experimental design is a structured investigation of whether a series of

factors, when varied, have an effect on the variable of interest (usually
referred to as the ‘Response Variable’ or ‘Quality Characteristic’)
! The statistically designed experiment involves varying two or more variables
simultaneously and obtaining multiple measurements under the same

experimental conditions
! This is known as Factorial design, and is an important method to determine
the effects of multiple variables on a response
Module 16
Design of Experiments
The advantages of this approach are as follows:

!  Interactions can be detected and measured
!  Each value does the work of several values.
!  A properly designed experiment allows you to use the same observation to
estimate several different effects; thereby reducing the number of
experiments
!  it can be used to find both main effects (from each independent factor) and
interaction effects (when both factors must be used to explain the outcome)
!  Experimental error is quantified
Module 16
The Goals of Design of Experiments
!  Problem solving
!  Eliminate defective products or services.
!  Reduce cycle time of handling transactional processes
!  Optimizing
!  Mathematical model is desired to move the process response
!  Robust design
!  Provide consistent process or product performance.
!  Desensitize the output response(s) to input variable changes
including NOISE variables.
!  Design processes knowing which input variables are difficult to
maintain
!  Screening
!  Narrowing of the critical factors
Module 16
Design of Experiments Definitions
!  Response variable: The variable being investigated, also called the

dependent variable, sometimes called simply response
!  Primary variables: The controllable variables believed most likely to have
an effect. These may be quantitative or qualitative
!  Background variables: Variables, identified by the designers of the
experiment, which may have an effect but either cannot or should not be
deliberately manipulated or held constant. They can contaminate primary
variable effects unless they are properly handled via blocks
Module 16
! Experimental error: The variation in data left over after all significant
sources of variability have been accounted for. It is is also a synonym for
residuals, the differences between observed values and values expected
based on the regression equation obtained from the analysis of the
experiment.
! Interaction: A condition where the effect of one factor depends on the level
of another factor
Module 16
! Replication: The collection of more than one observation for the same set of
experimental conditions. Allows the experimenter to estimate experimental
error, since variation exists when all experimental conditions are held
constant, the cause must be something other than the variables being
controlled
! Randomization: In order to eliminate bias from the experiment, variables not
specifically controlled as factors should be randomized
Module 16
Design of Experiments The Approach
1. Define the Experimental Goals

2. Select Response Variable (Quality Characteristic) – Usually the Critical Y
3. Choose factors, levels and ranges – Brainstorming & Cause and Effect
analysis can establish potential factors which may affect the Quality
Characteristic. Will need to change each factor at least once to observe the
difference it makes. Accordingly shall select 2 (or more) levels for the factor,
ensuring that the range is sufficient to have an effect, but not so large as to
move outside reasonable ranges
4. Select Experimental design
Module 16
5.  Perform the Experiment

6.  Analyze the outcomes
7.  Draw conclusions and make recommendations
Module 16
5.  Perform the Experiment

6.  Analyze the outcomes
7.  Draw conclusions and make recommendations
Module 16
Design of Experiments Factors
!  Factors are the main categories to explore when determining the cause
!  A level is basically one of the subdivisions that make up a factor
!  A group is set of conditions that will make up that particular experiment
!  Null outcome is when the outcome of your experiment is the same
regardless of how the levels within your experiment were combined
!  Main effect is when there exists a consistent trend among the different
levels of a factor
!  Interaction effect is when there is an interaction between the factors
Module 16
Design of Experiments Factor Notation
!  The notation used to denote factorial experiments conveys a lot of

information.
!  When a design is denoted a 23 factorial, this identifies the number
of factors (3);
!  How many levels each factor has (2);
!  And how many experimental conditions there are in the design
(23=8)
!  Factorial experiments can involve factors with different numbers of levels. A
243 design has five levels, four with two levels and one with three levels,
and has 16 X 3=48 experimental conditions
!  This default is the Full Factorials design, which is seldom used
Module 16
Design of Experiments Factorials
Fractional Factorials
! Consists of a carefully chosen subset (fraction) of the experimental runs of a
full factorial design
! The subset is chosen so to expose information about the most important
features of the problem studied, while using a fraction of the effort of a full
factorial design
! Notation is lk − p, where l is the number of levels of each factor investigated,
k is the number of factors investigated, and p describes the size of the

fraction of the full factorial used
! For example, a 25 − 2 design is 1/4 of a two level, five factor factorial design.
Rather than the 32 runs that would be required for the full 25 factorial
experiment, this experiment requires only eight runs
Module 16
! The levels of a factor are commonly coded as +1 for the higher level, and −1
for the lower level. For a three-level factor, the intermediate value is coded
as 0
! The points in a two-level factorial experiment are often abbreviated with
strings of plus and minus signs

! The strings have as many symbols as factors, and their values dictate the
level of each factor: conventionally, for the first (or low) level, and for the
second (or high) level
Module 16
!  They can also be abbreviated by (1), a, b, and ab
!  Where the presence of a letter indicates that the specified factor is
at its high (or second) level
!  And the absence of a letter indicates that the specified factor is at
its low (or first) level
!  For example, "a" indicates that factor A is on its high setting, while
all other factors are at their low (or first) setting
!  (1) is used to indicate that all factors are at their lowest (or first)
values
Module 16
!  Teams typically rely on statistical reference books to supply the "standard"
fractional factorial designs, consisting of the principal fraction.
!  The principal fraction is the set of treatment combinations for which the
generators evaluate to + under the treatment combination algebra
!  The design restricts focus to the interactions between pairs of factors
Module 16
!  Use aliasing to overcome disadvantage of only using two factors
!  In aliasing, interactions of more than two factors are represented as a single
new actor
!  For instance, a factorial design with three factors will not consider the
interaction between factors 1, 2, and 3, but instead will create a new factor
(4) representative of this interaction
!  The Problem with this approach is that the effects of factor 4 cannot be
estimated independent of the interactions of factors 1, 2, and 3. This is
referred to as confounded data
Module 16
! A fractional factorial experiment is generated from a full factorial experiment
by choosing an alias structure.

! The alias structure determines which effects are confounded with each other.
! For example, the five factor 25 − 2 can be generated by using a full three
factor factorial experiment involving three factors (say A, B, and C) and then
choosing to confound the two remaining factors D and E with interactions
generated by D = A*B and E = A*C.
! These two expressions are called the generators of the design.
! So for example, when the experiment is run and the experimenter estimates
the effects for factor D, what is really being estimated is a combination of the
main effect of D and the two-factor interaction involving A and B.
Module 16
!  An important property of a fractional design is its resolution or ability to

separate main effects and low-order interactions from one another
!  The most important fractional designs are those of resolution III, IV, and V:
Resolutions below III are not useful and resolutions above V are wasteful
Module 16
Fractional Factorials Resolutions
! I: Not useful: an experiment of exactly one run only tests one level of a factor
and hence can't even distinguish between the high and low levels of that
factor. e.g. 21 − 1 with defining relation I = A
! II: Not useful: main effects are confounded with other main effects e.g. 22 − 1
with defining relation I = AB

! III: Estimate main effects, but these may be confounded with two-factor
interactions e.g. 23 − 1 with defining relation I = ABC
Module 16
! IV: Estimate main effects unconfounded by two-factor interactions

Estimate two-factor interaction effects, but these may be confounded with
other two-factor interactions e.g. 24 − 1 with defining relation I = ABCD
! V: Estimate main effects unconfounded by three-factor (or less) interactions
Estimate two-factor interaction effects unconfounded by two-factor

interactions
Estimate three-factor interaction effects, but these may be confounded with
other two-factor interactions e.g. 25 − 1 with defining relation I = ABCDE
Module 16
!  NOTE: The resolution described is only used for regular designs

!  Regular designs have run size that equal a power of two, and only full
aliasing is present.
!  Non-regular designs are designs where run size is a multiple of 4; these
designs introduce partial aliasing, and generalized resolution is used as
design criteria instead of the resolution described previously
Module 16
!  In the analyze stage, fractional factorial designs are used to identify process
drivers and sources of variation
!  In the improve stage, fractional factorial designs are used along with center
points to estimate the effects of curvature
!  Fractional Factorial design is common
Module 16
Response Surface Methods (RSM)

!  AKA Response Surface Analysis
!  Explores the relationships between several explanatory variables and one

or more response variables
!  Uses a sequence of designed experiments to obtain the best response
value
!  Used only during the Improve Phase
!  Used to map the response surface so the effects of varying certain factors
can be predicted
!  Also used to find the operating conditions that produce the desired
specifications
Module 16
Response Surface Methods (RSM)

!  This model is only an approximation, but use it because the model is easy
to estimate and apply, even when little is known about the process
!  RSM has an effective track-record of helping teams improve products and
services
Module 16
Response Surface Methods Process

Typically has three phases, 0 through 2
!  Phase 0 is considered a prerequisite phase. In this phase, the team uses
screening designs to create a critical set of significant factors. Then, a first-
order regression model is created
!  In Phase 1, the team will use the steepest ascent methodology to define the
operating region at present and identify the direction of maximum response
!  The first-order regression model created during phase 0 can be very useful
at this point, because its scale is great enough to ensure that the data
points are affected by first-order effects
Module 16
Response Surface Methods Process Phase 1

! Phase 1 includes the application of steepest ascent methodology to a first-
order regression model

! Data points are collected along the steepest path beginning with the design
center, or the spot where (x1, x2) = (0, 0). This design center is the first test
condition
! The steepest ascent is determined by moving β1 coded units in the x1
direction for every β2 coded units in the x2 direction, where β1 and β2 are the
coefficients of the x1 and x2 terms, respectively
! If the changes are sufficiently small, then obtaining a good picture of the
response will be possible
Module 16
Response Surface Methods Process Phase 1

! Given a specific change in uncoded units for x1, it will be possible to obtain
values for x2, β1, and β2

! It also is possible to determine the path of steepest ascent relative to the
physical limitations of the system, such as if either x1 or x2 cannot proceed

beyond a certain point
! The local maximum conditions are determined by looking for the point at
which the response begins to diminish

! Once the local maximum condition has been determined, another
experiment is run near this point to obtain a first-order model with

centerpoint(s)
Module 16

!  Phase 1: After a first-order model has been conducted near the maximum
at the end of phase 1, there should be several redundant runs to estimate

lack of fit
!  When the lack of fit is insignificant, a new path of steepest ascent may be
found by adjusting the intervals, starting point, or direction

!  If the lack of fit is significant and there is curvature, the point likely is close
to a maximum, minimum, or mini-max. At this juncture it now is time to

begin phase 2
Module 16

! Phase 2 the application of ridge analysis and a second-order regression
model to locate the optimal conditions at stationary points in a small region.

! In response surface analysis, a stationary point is defined as anywhere that
the slope of the second-order response surface model is zero for each of the
factors
! Stationary points may be a maximum value, a minimum value, or a “mini-
max” value, which is the highest or lowest point in a saddle curve

! If the stationary point is significantly outside the data range, it may be used
only to obtain direction
Module 16
Response Surface Methods Process Interpretation
!  Generates charts that can be subjected to analysis of variance.
!  The F statistic can be used to compare the sum of squares variation caused
by pure error with the sum of squares variation caused by curvature

!  If the curvature is significant, the point likely is close to a local maximum,
minimum, or mini-max (that is, a stationary point)

!  If the stationary point falls outside the experimental region, then new data
must be required so the region can be enlarged

!  If this is impossible because the data point falls in a region that would be
impossible to reproduce, then constrained optimization should be applied to

the steepest ascent methodology
Module 16
Response Surface Methods Process Interpretation
!  If the stationary point is determined to be a mini-max, then constrained
optimization techniques must be applied to the steepest ascent

methodology.
!  The full results then can be analyzed after axial points are added to the
design at the new centerpoint

!  These axial points are placed on the design at places where they will
achieve rotatable orthogonal design.

!  Again, it is necessary to collect new data around the optimal point for the
purpose of verification
Module 16

Phase 2 .
!  The next step is to create response surface and contour plots for each two
factors.
!  Then, identify the stationary point in the response surface and contour plots.
!  Next, predict the response at the optimum using the second-order
regression model .
!  Finally, verify the model by gathering new data in the region around the
optimum
Module 16
Design of Experiments Experimental designs
!  Fixed-effects model: An experimental model where all possible factor

levels are studied. For example, if there are three different materials, all three
are included in the experiment
!  Random-effects model: An experimental model where the levels of factors
evaluated by the experiment represent a sample of all possible levels.For

example, if we have three different materials but only use two materials in
the experiment
Module 16
! Mixed model: An experimental model with both fixed and random effects
! Completely randomized design: An experimental plan where the order in
which the experiment is performed is completely random

! Randomized-block design: An experimental design is one where the
experimental observations are divided into ‘‘blocks’’ according to some

criterion. The blocks are filled sequentially, but the order within the block is
filled randomly
Module 16
Latin-square designs: Designs where each treatment appears once and

only once in each row and column.
A Latin-square plan is useful when it is necessary or desirable to allow for two

specific sources of non-homogeneity in the conditions affecting test results. !
for example, machines, positions, operators, runs, days. A third variable is
then associated with the other two in a prescribed fashion
The use of Latin squares is restricted by two conditions:

!  The number of rows, columns and treatments must all be the same
!  There must be no interactions between row and column factors
Module 16
DOE graphs and plots
Interaction plots
!  Illustrate the interrelationships of three parameters. In most cases, these
parameters are two factors and one response
!  Useful for evaluating the results of designed experiments and multiple
regression
!  Typically, plot variables are placed on the x-axis, and the responses are
placed on the y-axis
!  The distinct lines on the plot are defined by the levels of the interaction
variable
Module 16
Interaction plots
!  The distinct lines on the plot are defined by the levels of the interaction
variable
!  If the plot variables exhibit no interaction, then the lines basically will be
parallel. That is, both plot variables will produce similar trends when
combined with the response variable.
!  If the lines are not parallel, however, an interaction likely exists
Module 16
Both main effects and no interaction
Module 16
Both main effects with an interaction
Module 16
Group main effect, an interaction, and no Condition effect
Module 16
Group main effect , no Condition effect, and no interaction
Module 16
A crossover interaction and no main effects
Module 16
No main effects, no interaction
Module 16
Cube
Module 16
Module 16
Contour plots
!  Are composed of groups of curves
!  Each of these curves is assigned a constant value according to a fitted
response
!  The path of each of these curves relates to values that have been
separated at regular intervals

!  Any additional factors are placed on the chart according to their mean
or some other value

!  They are used in response surface analysis to estimate the maximum
and minimum responses associated with particular ranges of data
Module 16
Contour plots
!  If there are only first-order main effects, the contour plot will have
parallel lines separated from one another by equal distance.

!  Whenever interactions occur between the responses, the contour lines
curve.
Module 16
End
!  Improve Phase Overview
!  Basic DOE terms & Designs
!  DOE Graphs and Plots
Module 16
Module 17 – Improve Phase – Root Cause Analysis
Root Cause Analysis
Outline
1. Root Cause Analysis
2. Titanic case study
Module 17 586
Root Cause Analysis
Root Cause Analysis
! Use cause and effect diagrams, relational matrices, and other problem-
solving tools to identify the true cause of a problem
! Derivative of FMEA
! It is not the initial response to the problem
! Nor is it a restatement of the findings
! Usually the root cause is a process, procedure or organizational failure
Module 17 587
Root Cause Analysis
Root Cause Analysis

!  Standard process for;
!  Identifying a problem
!  Containing and analyzing the problem
!  Defining the root cause
!  Defining and implementing the actions required to eliminate the root
cause
!  Validating that the corrective action prevented recurrence of problem
!  Features interdisciplinary involvement of those closest to and/or most
knowledgeable about the situation
Module 17 588
Root Cause Analysis
The Root Cause is
!  The causal or contributing factors that, if corrected, would prevent recurrence

of the adverse effect, defect or problem in question
!  The “factor” that caused the effect, problem or defect that can be
permanently eliminated through process improvement
!  The factor that sets in motion the cause and effect chain that creates a
problem
!  The “true” reason that contributed to the creation of a problem, defect or
effect
Not finding the root cause can lead to costly band aids and rabbit holes
Module 17 589
Root Cause Analysis
Why do Root Cause Analysis

!  Prevent problems from recurring
!  Reduce possible injury to personnel
!  Reduce rework and scrap
!  Increase competitiveness
!  Promote happy customers and stockholders
!  Ultimately, reduce cost and save money
Module 17 590
Root Cause Analysis
Root Cause Analysis
The usual approach a low Sigma organizations take.
1.  A problem hits
2.  Fire fighting
3.  Blame someone / CYA all-around
4.  The problem hits again or some 'new' problem caused by the fire fighting
5.  Return to step 2... rinse and repeat
The problem with the above is...

The initial response is usually the symptom, not the root cause of the
problem. Then there is the blame game...
Module 17 591
Root Cause Analysis
Root Cause Analysis
The RCA approach.
1.  Problem manifests
2.  Problem identified
3.  Containment of problem and process
4.  Follow defined RCA process
5.  Solution validated
6.  Solution fully implemented
Module 17 592
Root Cause Analysis
Root Cause Analysis
Ditch the blame game
!  Most human errors are due to a process error e.g. Titanic sinking
!  A sufficiently robust process can eliminate human errors
!  Placing blame does not correct a root cause situation

!  Is training appropriate and adequate?
!  Is documentation available, correct, and clear?
!  Are the right skillsets present?
Module 17 593
Root Cause Analysis
Root Cause Analysis
Corrective Action
! Immediate
! Preventive – Process focused
! Preventive – System focused
Module 17 594
Root Cause Analysis
Root Cause Analysis
When do you do RCA
!  Significant or consequential events

!  Repetitive human errors are occurring during a specific process
!  Repetitive equipment failures associated with a specific process
!  Performance is generally below desired standard
Module 17 595
Root Cause Analysis
Root Cause Analysis
General Approach to RCA
!  Assign the task to a team knowledgeable of the systems and processes

involved; or at the very least have access to SMEs
!  Define the problem
!  Collect and analyze facts and data
!  Develop theories and possible causes - there may be multiple causes that
are interrelated
!  Systematically reduce the possible theories and possible causes using the
facts
Module 17 596
Root Cause Analysis
Root Cause Analysis
General Approach to RCA
!  Develop possible solutions
!  Define and implement an action plan
!  Monitor and assess results of the action plan for appropriateness and
effectiveness
!  Repeat analysis if problem persists- if it persists, did we get to the root
cause... Obviously not
Module 17 597
Root Cause Analysis
Root Cause Analysis
Four Rules for RCA
1. Causal Statements must clearly show the "cause and effect" relationship
2. Negative descriptors are not used in causal statement
3. Each human error must have a preceding cause
4. Each procedural deviation must have a preceding cause
Module 17 598
Root Cause Analysis
Root Cause Analysis
Common Errors
! Looking for a single cause- often 2 or 3 which contribute and may be
interacting
! Ending analysis at a symptomatic cause
! Assigning as the cause of the problem the “why” event that preceded the real
cause
Module 17 599
Root Cause Analysis
Root Cause AnalysisTools
! The “5 Whys”
! Pareto Analysis (Vital Few, Trivial Many)
! Brainstorming
! Flow Charts / Process Mapping
! Cause and Effect Diagram
! FMEA
Module 17 600
Root Cause Analysis
The “5 Whys” (aka Questioning the Void)
Ask “Why?” five times
! 
!  Stop when the corrective actions do not change
!  Stop when the answers become less important
!  Stop when the root cause condition is isolated
Module 17 601
Root Cause Analysis
Cause and Effect Diagram
!  AKA Fishbone Diagram or Ishikawa Diagram
!  Identifies many possible causes for an effect or problem
!  Excellent structured brainstorming tool
!  Sorts ideas into useful categories.
Module 17 602
Root Cause Analysis
Cause and Effect Diagram Example
Module 17 603
Root Cause Analysis
Cause and Effect Diagram Creation
1. Agree on a problem statement (effect). Write it at the center right of the
flipchart or whiteboard. Draw a box around it and draw a horizontal arrow
running to it.
2. Brainstorm the major categories of causes of the problem. If this is difficult
use generic headings such as:
!  Methods
!  Machines
!  People
!  Materials
!  Measurement
!  Environment
Module 17 604
Root Cause Analysis
3. Write the categories of causes as branches from the main arrow.
4. Brainstorm all the possible causes of the problem. Ask: “Why does this
happen?”
5. As each idea is given, the facilitator writes it as a branch from the
appropriate category.
6. Causes can be written in several places if they relate to several categories
7. Again ask “why does this happen?” about each cause. Write sub–causes
branching off the causes.
8. Continue to ask “Why?” and generate deeper levels of causes. Layers of
branches indicate causal relationships
9. When the group runs out of ideas, focus attention to places on the chart
where ideas are few
Module 17 605
Root Cause Analysis
10. After completing the Cause-Effect Diagram, take the following actions:
!  Rank the ideas from the most likely to the least likely cause cause
of the problem or issue
!  Develop action plans for identifying the essential data, resources
and tools
Module 17 606
Root Cause Analysis
Corrective Action Plan
!  Must verify the solution will eliminate the problem
!  Verification before implementation whenever possible
!  Define exactly
!  What actions will be taken to eliminate the problem?
!  Who is responsible?
!  When will it be completed?
!  Make certain customer is happy with actions
!  Define how the effectiveness of the corrective action will be measured.
Module 17 607
Root Cause Analysis
!  To be Credible a Root Cause Analysis must:
!  Include participation by the leadership of the organization & those
most closely involved in the processes & systems
!  Be internally consistent.
Module 17 608
Root Cause Analysis
Titanic Case Study
! At 11:40 P.M. on Sunday, April 14, 1912, the RMS Titanic struck an iceberg
at a speed of 22.5 knots
! The officer of he watch ordered engines reversed which made it impossible
to turn in time
! The "watertight" compartments of the Titanic's hull were not actually
watertight. They were open at the top

! Five compartments flooded. The ship was designed to stay afloat with four
flooded
! 1,503 people total died, including passengers and crew – mostly from
hypothermia in the 31 degree water

! There were 472 lifeboat seats not used
So lets do a RCA...
Module 17 609
Root Cause Analysis
Titanic RCA
Module 17 610
End
Root Cause Analysis
Root Cause Analysis
! 
Titanic case study

! 
Module 17 611
Module 18 – Improve Phase – Lean Tools
Lean Tools
Outline
1. Kaizen and Kaizen Blitz
2. Waste elimination
3. Cycle-time reduction
Module 18 613
Lean Tools
Kaizen;
!  Kaizen is a philosophy of continuous improvement
!  Improvements are based on the insights and experiences of lower-level
employees, as opposed to the traditional executive-driven Western model

!  Can be successful only with adequate training, defined operating practices,
and buy-in from all employees

!  Constant communication exists
!  Focus is small improvements, not breakthrough changes
!  Driven from the bottom-up
!  Based on the premise that the people who do the work know it best
Module 18 614
Lean Tools
Kaizen Goals;
!  Enhance capacity
!  Reduce waste
!  Increase productivity
!  Reduce inventory
!  Improve flow - Flow-pull-perfection
Module 18 615
Lean Tools
Eight Rules of Kaizen
1. Discard conventional thinking concerning processes
2. Think of how we can do, not why we can't
3. Do not accept excuses
4. Question everything
5. Immediately correct mistakes
6. Seek root causes
7. Depend on the wisdom of 10 people, not the knowledge of 1
8. Do something now rather than seeking perfection later
Module 18 616
Lean Tools
Kaizen Blitz (aka Kaizen Event)
!  Whereas Kaizen focuses on making small, evolutionary changes, a Kaizen
blitz focuses on making a rapid improvement in a manner of days (usually

5), though planning can take longer
!  Executed by a team assembled for the purpose
!  Primary vehicle for change in organizations implementing Lean
Module 18 617
Lean Tools
Kaizen Blitz Team Composition
! Quality champion - sets the strategic direction, provides focus, assigns
resources, and defines accountability. Often a Master BB

! Sponsor - accountable for success of the kaizen blitz. Deals with
impediments to the team's efforts

! Kaizen facilitator - an expert in the kaizen methodology. Prepares, designs,
and facilitates the sessions

! Participants – provide SME knowledge and other skills
Module 18 618
Lean Tools
Kaizen Blitz Phases
1. Kick off – Project definition and any Kaizen blitz training needed
2. Problem identification – Create process map and initial data collection
3. Analyze Data
4. Develop solution(s) – Start implementing them
5. Present results and solutions
Module 18 619
Lean Tools
Kaizen Blitz Traps
!  Lack of management support
!  Superficial training (due to limited time), resulting in poor understanding of
Lean principles
!  Lack of buy-in to proposed changes from those not involved in the event
!  Insufficient data to arrive at robust analysis of root causes
!  Lack of implementation during the event
!  Delays in implementation after the event
!  Lack of sustainability after the event
Module 18 620
Lean Tools
Kaizen Blitz Traps
! Has severe limitations when looking at extensive, complex, cross-functional
systems
! When the process/problem can’t be easily defined, or is associated with
multiple root causes, a Blitz is unlikely to be of much use

! Can be misused by organizations that want a quick-fix to deep-rooted
problems
However, if a Blitz is tightly defined and when there is clear scope to

implement changes quickly, it can lead to significant, measurable,
improvements
Module 18 621
Lean Tools
Kanban
! Kanban is faster, more efficient, and saves significant money over most other
production models
! Reduces inventory, on average, by 25 to 75%
! The visually organized environment ensures all parts are easily found and
continually stocked
! The speed of moving from one task to another is significantly reduced by the
creation of clearly marked flow lanes, kanban cards, and clearly marked
labels
Module 18 622
Lean Tools
Kanban
! Translates as card signal
! Signals the start of an event
! Use either a physical 'card' or electronic signal
! Pull system with the goal of reducing inventory by producing only what is
ordered, when its ordered, and only the quantity ordered

! Increased flexibility to meet customer demand
! At its core, it requires one to visualize the workflow and reduce WIP
! Bottlenecks become visible in realtime
Module 18 623
Lean Tools
Rules of Kanban
! The Parts Are Always Withdrawn From The Prior Process
! Produce Only What Is Necessary To Replenish The Quantity Withdrawn
! Never Pass on A Bad Part
! Level Load Production, Rapid Changeover, Small Lot Production, Zero
Defects
! Kanban Is Used To Fine Tune (Not Provide For Major Changes)
! The Process Must Be Capable Of Producing Good Parts (Rational And
Stable)
Module 18 624
Lean Tools
Rules of Kanban
! Need Efficient Methods Of Transportation, Shortest Routes Possible
! Disciplined Organization
! Nothing Is Made or Transported Without A Kanban.
! Kanban Cards Always Accompany the Parts Themselves.
! The Number of Kanbans Should Decrease over time
Module 18 625
Lean Tools
Types of Kanban
The two basic types of Kanban are:
!  Production (P) Kanban A P-kanban, when received, authorizes the
workstation to produce a fixed amount of products

!  The P-kanban is carried on the containers that are associated with it
!  Transportation (T) Kanban A T-kanban authorizes the transportation of the
full container to the downstream workstation

!  The T-kanban is also carried on the containers that are associated with the
transportation to move through the loop again
Module 18 626
Lean Tools
Waste Elimination
! Waste is any activity that doesn’t add value, as defined by the customer, to
the end product or service

! Ask two questions:
1.  Is your customer willing to pay for this activity?

2.  Does this activity add value to a process that adds direct customer
value?
! No to either means it's waste, though you still have to watch for more subtile
forms of waste; such as rework and inspection
! You will never get rid of all non-value-adding activities due the regulatory or
compliance activities
Module 18 627
Lean Tools
The 7 Wastes (Muda)
1. Overproduction
2. Waiting
3. Transporting
4. Overprocessing
5. Excess Inventory
6. Excess Motion
7. Defects
Module 18 628
Lean Tools
Waste #1: Overproduction
!  Making too much or too early
!  Usually because of working with oversize batches, long lead times, and
poor supplier relations or supplier quality
!  Overproduction leads to high levels of inventory
!  The aim should be to make only what is required when it is required by the
customer
Module 18 629
Lean Tools
Waste #2: Waiting
!  Time wasted waiting for whatever is needed to proceed
!  Includes WIP waiting in your process queues
!  This disrupts flow and adversely impacts cycle time
Module 18 630
Lean Tools
Waste #3: Transportation
!  Movement of materials from one location to another adds zero value to the
product
!  Can be a very high cost as one need people to operate it and equipment
such as trucks or fork trucks to undertake this expensive movement of
materials
!  Also results in the waiting waste as one waits for the shipment to arrive
!  Internally, use spaghetti diagrams to map out the transportation of goods
within your facility
!  Try and source from suppliers as close as possible to your facilities
Module 18 631
Lean Tools
Waste #4: Overprocessing
!  Inappropriate techniques, oversize equipment, working to tolerances that
are too tight, performing processes that are not required by the customer
and so forth
!  Impacts cycle times, contributes to waiting, excess motion, excess
inventory, and increases the risk of defects
Module 18 632
Lean Tools
Waste #5: Excess Inventory
!  Every item in inventory ties up money, resources and space and until it is
actually sold the 'asset' value is not realized

!  It also may be damaged or deteriorate during storage and could become
obsolete if in inventory long enough
Module 18 633
Lean Tools
Waste #6: Excess Motion
!  Unnecessary motions are those movements of man or machine which are
not as small or as easy to achieve as possible

!  Excessive travel between work stations, excessive machine movements
from start point to work start point

!  Cost time and money, increases the risk of injury or machine wear and tear
Module 18 634
Lean Tools
Waste #7: Defects
!  Quality errors that cause defects invariably cost far more than you expect.
Every defective item requires rework or replacement

!  it wastes resources and materials
!  it creates paperwork,
!  it can lead to lost customers. Or even lawsuits and fines
Module 18 635
Lean Tools
Two other key concepts related to waste;
Muri (Unreasonableness)
!  All the unreasonable work imposed on workers and machines because of
poor organization or short-sighted focus on costs

!  It is pushing a person or a machine beyond its natural limit
!  Bad working conditions
!  Almost always a cause of multiple nonconforming conditions and defects
Mura (Inconsistency)
!  Variation and inconsistency in quality and volume in both products and
working conditions
Module 18 636
Lean Tools
5S;
!  An essential step required for Waste Elimination
!  Foundational to Kaizen
!  It is a valuable strategy for reducing cycle time that does not add value and
that is lost to movement, finding lost materials, and inefficiently using the
physical space
!  May also be used to accelerate inventory processes and to diminish
accidents in the workplace
!  Represents 5 disciplines for maintaining a visual workplace and a
standardized workplace
Module 18 637
Lean Tools
5S Stands for;
Sort – Red tag and remove unnecessary items and either store or dispose of
them properly
Straighten or Streamline - Arrange all necessary items in order so they can
be easily picked for use
Shine or Sweep - Clean and inspect the workplace completely
Standardize - Maintain high standards of workplace organization at all times.
Maintain everything according to its standard
Sustain - Keep in working order and perform regular audits
Module 18 638
Lean Tools
5S Things to do overall;
! Develop a map identifying the access ways and the “action” areas
! Perform any necessary realignment of walkways, isles, entrances
! Assign an “address” to each of the major action areas
! Mark off the Walkways, Aisles & entrances from the action areas
! Apply flow-direction arrows to aisles & walkways
! Perform any necessary realignment of action areas
! Mark-off the inventory locations
! Mark-off equipment/machine locations
! Mark-off storage locations( Cabinets,shelves,tables
! Color-code the floors and respective action
Module 18 639
Lean Tools
Sort Things to do;
! Start with a red tag campaign
! Tag everything that looks disorderly or unsafe
! Be ruthless
! If in doubt throw it out
! If still in doubt, send it to a “red tag area” for resolution
! You should be removing truckloads of items… be tough
Module 18 640
Lean Tools
Straighten & Streamline Things to do;
!  Create a place for everything
!  Determine what should be where
!  Deal with the open red tags from the Sort step:
!  Organize parts and material
!  Resolve things you were afraid to throw out
!  Write off or sell off obsolete materials
!  Map and and mark clear lanes and paths
!  Color code tool and material locations
Module 18 641
Lean Tools
Shine Things to do;
! Make the work area absolutely clean
! Clean everything (equipment, floors, walls…)
! Paint everything (equipment, floors, walls…)
! Look for problems…
!  Leaks?
!  Loose or missing items
!  Unsafe conditions
!  Causes of messes or problems…
!  Quality issues caused by dirt and clutter
Module 18 642
Lean Tools
Standardize Things to do;
!  SOP to keep the area clean, safe and orderly?
!  Agree on daily and weekly tasks
!  Standardize our processes
!  The devil is in the details and so should we
!  Establish a visual management system for these tasks
!  Shadow all tools
Module 18 643
Lean Tools
Sustain Things to do;
!  Develop audit checklists
!  Assign the audit role to someone outside the area
!  Track the audit results
!  Make 5S a daily habit... Being OCD is good
!  Set the example
Module 18 644
Lean Tools
Are we finished yet? Have we:
!  Removed unnecessary items
!  Stored everything in a neat manner
!  Cleaned the floors of debris, oil and dirt
!  Updated and straightened the bulletin boards
!  Ensured that access to emergency equipment is easy and highly visible
!  Ensured that items on floors are in clearly marked areas
!  Ensured that aisles are clear and kept free of material
!  Boxes are stored in an neat, orderly fashion
Module 18 645
Lean Tools
Are we finished yet? Have we:
!  Cleaned all machines, tools, and equipment
!  Made sure that there is nothing on top of machines or cabinets
!  Stored all documents and binders in a neat manner
!  That all tools, jigs, and fixtures are labeled, shadowed, identified, and easy
to reach
!  That all shelves, benches, desks are kept free of unused objects, including
files and documents
Module 18 646
Lean Tools
Visual Management uses;
!  Floor and surface marking
!  Shadow boxes
!  Samples
!  Visual indicators
!  Obstacle height limits
!  Lights and sounds
!  Arrows, zones, stickers
!  Scoreboards
!  Labels and tags
Module 18 647
Lean Tools
Module 18 648
Lean Tools
Standard Work
!  Standard work is one of the most powerful but least used lean tool
!  By documenting the current best practice, standard work forms the baseline
for Kaizen
!  As the standard is improved, the new standard becomes the baseline for
further improvements
!  Each step in the process should be defined and must be performed
repeatedly in the same manner

!  Any variations in the process will most likely increase cycle time and cause
quality issues
Module 18 649
Lean Tools
Standard Work consists of three elements;
!  Takt time, which is the rate at which products must be made in a process to
meet customer demand

!  The precise work sequence in which an operator performs tasks within takt
time
!  The standard inventory, called the Standard WIP (SWIP), including units in
machines, required to keep the process operating smoothly without

incurring excess inventory or WIP
Module 18 650
Lean Tools
Standard Work supports the lean system of continuously improving capacities
and efficiencies by defining 5 critical elements for each process:
1. The customer demand

2. The most efficient work routine (steps)
3. The cycle times required to complete work elements
4. All process quality checks required to minimize defects/errors
5. The exact amount of work in process required
Module 18 651
Lean Tools
Steps for Creating Standard Work;
1. Define the extent of the process for which you are creating standard work
2. Determine the appropriate standard work requirements
3. Gather the required information
4. Create the standard work documents
5. Train the supervisor on the standard work
6. Train the employees to do the standard work
7. Run the process and observe the results
8. Make adjustments and modifications to the standard work
Module 18 652
Lean Tools
Dos and Don't for Creating Standard Work;
DO:
!  Keep standard work simple
!  Make it accessible
!  Include all info on one, easy-to-read document
!  Create one standard work document for each part of the process
!  Always look for ways to improve the process
DON'T
!  Put standard work in a desk drawer
!  Change processes without changing standard work
!  Make standard work difficult to change
!  Give up on standard work
Module 18 653
Lean Tools
Poka-Yoke - Error-Proofing ;
! Poka-yoke states that preventing errors is better than detecting them as
rework is a non-value-added activity

Processes must be rigorously analyzed and improved so the frequency and
! 
severity of mistakes is reduced

Options for error-proofing include; auto-correcting systems, auto-shutdown,
! 
jigs, digital counters, and warning systems
Module 18 654
Lean Tools
Cycle-time Reduction
Two process types:
1. Discrete
2. Continuous
Three main flow structures:

1. Convergent - several inputs feed one output
2. Divergent - several outputs derived from one input
3. Linear
Module 18 655
Lean Tools
Cycle-time Reduction
Key Concept is process throughput
!  IN(t) = Arrival/Inflow rate of jobs at time t
!  OUT(t) = Departure/Outflow rate of finished jobs at time t
!  IN = Average inflow rate over time
!  OUT = Average outflow rate over time
Stabilize first before tackling cycle time reduction

IN=OUT
Module 18 656
Lean Tools
Cycle Time
The difference between a job’s departure time and its arrival time = cycle
time. Also referred to as throughput time
Includes both value adding and non-value adding activity times
Processing time
Inspection time
Transportation time
Storage time
Waiting time
Cycle time is a powerful tool for identifying process improvement potential
Module 18 657
Lean Tools
Cycle Time
Little's Law
!  CycleTime = WIP/Throughput
Must account for

!  Rework
!  Multiple paths
!  Parallel activities
Module 18 658
Lean Tools
Reducing cycle times through process redesign;
!  Eliminate activities
!  Reduce waiting and processing time
!  Eliminate rework
!  Perform activities in parallel
!  Move processing time to activities not on the critical path
!  Reduce setup times and enable batch size reduction
Module 18 659
Lean Tools
Pull
! Increases throughput
! By pulling material in small lots, inventory cushions are removed, exposing
problems and emphasizing continual improvement

! Manufacturing cycle time is reduced
! Ideal situation is to have lot sizes of one pulled from one process to the next
! Lot sizes can be reduced by;
!  Improving material handling

!  Reducing setup times
!  Reducing setup costs
Module 18 660
Lean Tools
JIT Scheduling
!  Process frequent small batches rather than a few large batches
!  Make and move small lots so the level schedule is economical
!  Because lead times are shorter, quality problems are exposed sooner
!  Better quality means fewer buffers and allows simpler JIT systems to be
used
Module 18 661
Lean Tools
Continuous Flow
!  Takt time represents customer demand rate
!  Calculate the takt time = number ordered/time in shift
!  Goal is to precisely synchronizes the cycle time to the takt time
Module 18 662
Lean Tools
Continuous Flow
!  The creation, ordering, and provision of any good or any service can be
made to flow
!  Think about ways to;
!  Line up all of the essential steps needed to get a job done

!  Obtain a steady, continuous flow
!  No wasted motions
!  No interruptions
!  No batches or queues
!  Focus on the actual object or service
!  Ignore traditional boundaries
Module 18 663
Lean Tools
Level Loading
!  Its purpose is to regulate and moderate the flow of orders in a particular

process. Level loading typically is performed during the improve stage
!  Can be used to reduce the need for inventory checks during a process
!  Before it can be implemented, protocols must be standardized and
employees must be trained
!  The intention is to eliminate wait time at the beginning of a given process
!  Therefore, each completed unit should begin the next phase of the
production process immediately
Module 18 664
Lean Tools
Implementing Level Loading

!  First step in level loading is to calculate the takt time
!  The takt time is the demand divided by the amount of time available
!  Takt time should be posted at the work station, and resources should be
aligned with it
!  When variations in demand exist, needs for increased resources also will
exist
Module 18 665
End
Lean Tools
! Kaizen and Kaizen Blitz
! Waste elimination
! Cycle-time reduction
WE WILL NOW REVIEW THE IMPROVE PHASE
Module 18 666
Improve Phase – Summary
!  Define the short-list of critical X's
!  Ensure that they are actually X's and that they are controllable
!  Select you improvement approach
!  Ensure you have necessary buy-in to implement the improvements
Improve Phase Summary &

Review Questions
Improve Phase – Summary
Questions to ask at end of phase:
!  What critical X's did we uncover?
!  Have we missed anything?
!  Have our improvement initiatives resolved the problems?
!  Do we need any follow-up initiatives?

Review Questions
Improve Phase – Review Questions
Improve Phase Review Question 1
When conducting Hypothesis Analysis one must use the formula shown to
determine if a certain value is between – 1 and + 1 which will lead to a
conclusion relative to the hypothesis.
The value calculated by this formula
is the ________________________
a. Proportion of +/- 2 Standard Deviations to the total

b. Spread of the hypothesis data
c. Population Correlation Coefficient
d. Sample Correlation Coefficient
Review Questions
Improve Phase Review Question #1 Answer
1. D Sample Correlation Coefficient

Review Questions
When doing a graphical analysis of DOE results a Belt frequently uses the
Main Effects Plot. To determine the relative impact of a variety of inputs on
the output of interest it is easy to identify the most impactful input because the
slope of the line on the Main Effects Plot is __________________.
a. The steepest
b. Negatively correlated
c. Positively correlated
d. The shallowest

Review Questions
2. A The steepest

Review Questions
A ____________________ is used to create a model of the affect on an
output by the variation in two or more of the inputs
a. Correlation Coefficient
b. Linear Regression
c. Multiple Regression
d. X-Y Diagram

Review Questions
3. C Multiple Regression

Review Questions
Module 19 – Control Phase – Statistical process control (SPC)
Module 19 – Control Phase –
Statistical process control (SPC)
Outline
1.  Control Phase Overview
2.  SPC Basics
3.  Control Plan
4.  Control Charts
5.  Rational Subgrouping
Module 19 676
Control Phase Overview
!  The primary objective of the Control phase is to ensure that the gains
obtained during Improve phase are maintained long after the project has
ended
!  To that end, it is necessary to standardize and document procedures, make
sure all employees are trained and communicate the project’s results
!  In addition, the project team needs to create a plan for ongoing monitoring
of the process and for reacting to any problems that arise
!  And finally close out the project
Module 19 677
Statistical Process Control (SPC)
SPC Basics
!  Statistically-based quality control method
!  Goal is to ensures that the process operates at its full potential
!  Make as much conforming product as possible with a minimum of waste
!  Can be applied to any process where the conforming product output can be
measured
!  Emphasis on early detection
Module 19 678
SPC Basics
!  Variability is inherent in every process
!  Provides a statistical signal when assignable causes are present
!  Detect and eliminate assignable causes of variation
!  Natural variations in the production process are to be expected

!  Output measures follow a probability distribution
!  For any distribution there is a measure of central tendency and
dispersion
Module 19 679
SPC Basics
Implemented in 2 phases:
!  The first phase is the initial establishment of the process
!  The second phase is the regular production use of the process
Involves three main phases of activity:

!  Understanding the process and the specification limits
!  Eliminating assignable sources of variation, to stabilize the process
!  Monitoring the ongoing production process, assisted by the use of control
charts
Module 19 680
SPC Basics - Variation
!  Common-cause variation - Natural and random variations
!  Common-cause variation will influence each iteration of the process and
therefore will not be obvious on a control chart, so will be difficult to

diagnose
!  Special-cause variation - Unusual, unexpected, or sporadic variation
!  On a control chart, special variation will be indicated by points that lie far
outside the normal range
Module 19 681
SPC Basics - Variation
!  Assignable Variation
–  Variations that can be traced to a specific reason

–  The objective is to discover when assignable causes are present
and eliminate them
Module 19 682
!  The characteristics that need to be monitored and controlled will be listed
along the left side of the control chart
!  For each characteristic, there will be a:
!  Specification
!  measurement technique
!  Sample size
!  Sample frequency
!  Analytical tool
!  Reaction protocol
Module 19 683
Recalculating Control Limits
!  At the end of the Improve phase you may need to calculate new process
control limits and use these new limits as triggers for corrective action
!  If the answer to the following questions is yes, then proceed with calculating
new control limits. Any noes indicates the process does not have sufficient
statistical control to do so
!  The questions are;
!  Is there a statistical difference between the baseline and the new
measurements?
!  Is the rationale for the implemented change(s) understood?
!  Are the new measurements expected to represent the future performance?
Module 19 684
!  A control plan is a summary of the detection and/or prevention strategies
used to control processes or materials
!  Includes information such as the specification related to each relevant
characteristic
!  Used to record the strategy that will be used to control the key process
variables
!  Usually compiled from the results of designed experiments and FMEA
!  The FMEA is important as it indicates the most important sources of failure
!  Short and sweet. One page is the usual length
Module 19 685
!  In order for the control plan and SPC to be successfully implemented,
proper training and documentation needs to be provide
!  The new processes have to be properly documented and SOPs put into
place and enforced
!  Response plans need to be put in place should the processes fall out of
statistical control
Module 19 686
Control Charts
!  On a control chart, the specification is the objective range within which the
characteristic tolerably can fall
!  The control chart should indicate how the warblers will be measured and
how many measurements will be included in each sample
!  It should also indicate the frequency of sampling and the analytical tool to
be used to evaluate the sample
!  Finally it will will include the reaction rules for when a variable value falls
out of bounds
Module 19 687
SPC Charts
!  A time-ordered plot of the process data
!  The plot outlines the expected range of variation of the data
!  Since the expected range is known, anything outside of that needs
investigation and correction

!  Used to monitor your process Xs and/or your process Ys
!  Use when;
!  Process has a tendency to go out of control
!  Process is particularly harmful and costly if it goes out of control
Module 19 688
A process is in statistical control when;
!  No sample points outside limits
!  Most points near process average
!  About equal number of points above and below centerline
!  Points appear randomly distributed
Module 19 689
SPC Charts
!  There are two categories of SPC charts: Variable and Attribute;
!  Variable charts use continuous data

!  Sample size can be 2 to 10 parts
!  Attribute charts use discrete data, e.g. Pass/Fail
!  Sample size can be 50 to 100 parts
Module 19 690
Control charts for Variables
! X-bar ( ) charts control the central tendency of the process, can be
combined with the R chart to form the X-bar – R chart or with s chart to form
X-bar – s chart
–  Use with 1 to 10 rational subgroupings with R chart
–  Use with over 10 rational subgrouping with s chart
! R-charts control the range of the subgroups changes over time
! s-charts control the standard deviation of the process
! XmR charts are the same as X-bar except that it uses the median instead of
the average as a measure of central tendency

! I-mR charts are a combination of XbarR and XmR Chart. Gives both "within"
group and "between" group variation
Module 19 691
Control charts for Attributes
!  P-charts tracks the proportion of defective units in in a sample

!  C-charts tracks the number of defects in an item
!  U charts depict the percentage of samples that have a particular condition
in situations where sample sizes may vary and each sample may have
more than one occurrence of the condition
!  Np-charts measures the number of times a condition exists in each sample,
when the condition may occur only once and the sample size is consistent
Module 19 692
X-bar ( ) chart formula
Module 19 693
X-bar ( ) chart example
©Wikipedia
Module 19 694
R-chart formula
Module 19 695
R-chart example
©Wikipedia
Module 19 696
s-chart formula
Module 19 697
s-chart example
©Wikipedia
Module 19 698
X-bar ( ) chart Implementation
! X-bar charts are useful when subgroups of more than two observations can
be measured
! The x-axis of the X-bar chart is time, so the chart serves as a chronological
model of the process, moving from left to right

! Of course, all data entered into an X-bar chart must be assigned a time, or
else special-cause variation may not be noticeable

! If the size of the subgroup is greater than ten, then a range chart should not
be used to monitor process variation, because it will do a poor job of

estimating process sigma
! If the subgroup sizes are 1, then individual-X/moving-range chart may be
used
Module 19 699
X-bar ( ) chart Interpretation
! Before interpreting the X-bar chart, one must first examine the range chart
! When the range chart is out of control, the control limits on the X-bar chart
will not be useful

! After any points outside statistical control have been removed, the X-bar
chart may be interpreted relative to control limits and run-test rules

! Any points on the X-bar chart outside statistical control must be eliminated
Module 19 700
P-chart Formula
Module 19 701
P-chart example
©Wikipedia
Module 19 702
P-chart Interpretation
! All of the data points should lie between the upper and lower control limits. In
such a case, the process is said to be in statistical control

! As long as the data points remain within the control limits, any variation may
be attributed to common causes

! If all the data points are within the control limits, the process is said to be
within statistical control and future performance can be predicted

! However, if data points lie outside of the control limits, this must be blamed
on special causes of variation
©Wikipedia
Module 19 703
C-chart Formula
Module 19 704
C-chart example
©Wikipedia
Module 19 705
C-chart Interpretation
! The measured event may occur more than once in each unit of the sample
!  For instance, a C chart may be used to track errors in a particular process,
with the knowledge that several errors might occur in a single iteration of the
process
! All of the data points should lie between the upper and lower control limits. In
such a case, the process is said to be in statistical control

! As long as the data points remain within the control limits, any variation may
be attributed to common causes

! If all the data points are within the control limits, the process is said to be
within statistical control and future performance can be predicted

! However, if data points lie outside of the control limits, this must be blamed
on special causes of variation
©Wikipedia
Module 19 706
U-chart formula
Module 19 707
U-chart example
©Wikipedia
Module 19 708
U-chart Interpretation
! The upper and lower control limits indicate the boundaries of expected
process behavior
! The variation of points that lie within the control limits is attributed to common
causes, while any points outside the statistical control must be attributed to
special causes
! If no special-cause variation exists, then the process is stable enough to be
predictable
©Wikipedia
Module 19 709
Np-chart formula
Module 19 710
Np-chart example
©Wikipedia
Module 19 711
Np-chart Interpretation
! Depicts a stable process when all of the data points lie between the upper
and lower control limits

! Any variation within these limits is due to common causes, but any variation
that results in data points outside the control limits must be attributed to
special causes
! Data points that lie outside the control limits must be explained
! Typically, an Np chart is succeeded by experimentation aimed at diagnosing
particular causes
©Wikipedia
Module 19 712
I-mR chart formula
Module 19 713
I-mR chart example
©Wikipedia
Module 19 714
I-mR chart Interpretation
! After it is completed, it should be searched for special-cause variation
! Any special causes of variation must be identified and removed
! The general strategy when interpreting individual-X and moving-range charts
is to find non-random behavior or trends in the data

! One can use Run Tests for this
! Once a process has been observed for a sufficient time and is found to be in
control, calculating the process capability relative to requirements is possible

! However, it is not possible to predict the capability of a process not in
statistical control
Module 19 715
Rational Subgrouping
!  Is the process of organizing data into groups of items that were produced
under similar conditions in order to measure the variation between the

subgroups instead of between individual data points
!  The organization of subgroups is generally established to sample a subset
of the population within relatively homogeneous conditions

!  The subgrouping strategy directly determines the sensitivity, and therefore
the usefulness, of the control chart by bearing on the sampling plan for the
charts
!  Without a rational subgrouping strategy, the control charts will not answer
the right questions related to identifying the source of variability of a process
Module 19 716
Developing Rational Subgroupings
!  Consider the data source(s) and select the constant. e.g. the constant may
be a machine, plant, shift, etc.

!  Examine variability among the sources of data in order to define an
appropriate subgroup
!  To do so, consider the following questions:
!  What subgrouping strategy would produce ranges reflecting the

highest within- sample variation?
!  What strategy would produce ranges having the lowest within-
sample variation?
Module 19 717
Developing Rational Subgroupings
!  Establish the subgroups and calculate the range of variability for each group
!  The variation is within subgroups, not between them
!  Note: If you are uncertain with the choice and fear you may have selected
the wrong sub-grouping strategy, calculate ranges for both strategies and
evaluate
!  Use the understanding of how to group the data sources to move forward
and determine a sample frame for producing the desired control charts
Module 19 718
End
Statistical process control (SPC)

!  Control Phase Overview
!  SPC Basics
!  Control Plan
!  Control Charts
!  Rational Subgrouping
Module 19 719
Module 20 – Control Phase – Lean Tools for Process Control
Lean Tools for Process Control
Outline
1.  Visual Factory
2.  Total Productive Maintenance (TPM)
3.  Summary and Review of Control Phase
Module 20 721
Visual Factory
!  Describes visual methods a manufacturing plant can use to communicate
information about a process to everyone who needs to understand it as

they work
!  Use of visual tools will convey information in a clear, accurate, efficient, and
organized way to those who need to know it

!  Overall goal is to make the control and management of a company as
simple as possible
!  Visual Factory is implemented in two stages;
!  Determining what information needs to be communicated

!  How this information will be communicated
Module 20 722
Visual Factory
!  It prevents errors arising from miscommunication
!  It increases comprehension, even when describing complex processes
!  It makes employees feel more competent and reduces friction due to
misunderstanding about what is needed to be done

!  It improves the way machines are used
!  It decreases how long work stays in progress
KEY FACT: 83% OF THE INFORMATION WE ABSORB IS VISUAL
Module 20 723
Visual Factory Implementation
!  The current state must be compared to the future state goals in order to
determine what information is to be delivered

!  The information required to get from one state to another is what must be
conveyed
!  How the information is conveyed depends on the desired end result.
!  The location and method of information delivery also depends on the
relevancy of the information
Module 20 724
Visual Factory
Typically this data includes;
!  Process metrics
!  Work instructions
!  General plant information
Module 20 725
Visual Factory – Process Metrics
! The machine or operating unit will deliver real time metrics
! When there is instant information, adjustments can be made immediately to
a process
! A metric that communicates information through light is called an andon
(Japanese for lantern)

! Usually a central feature in a visual factory as it provides instant feedback on
the state of a process

! Gives the worker the ability to stop production when a defect is found, and
immediately call for assistance Indicates where the alert was generated, and
may also provide a description of the trouble
! One can have audio andons
Module 20 726
Visual Factory – An example of an Andon
Module 20 727
Visual Factory – Work instructions
! Graphics and photographs are preferred as they give clear instructions and
minimize errors in production

! The more accurate the graphic reflects the process, the higher the level of
communication
! Words and numbers can be interpreted in many ways because they are
constrained by rules of grammar or mathematical sequence and logic

! On the other hand, clear visual representation offers a literal description that
can be immediately understood

! Addresses ESL issues
Module 20 728
Visual Factory – Example Work instructions
Module 20 729
Visual Factory – General Plant Information

! Usually posted in a central location and stimulates two-way information
exchanges
! Visual information raises awareness, alerts about changes, posts warnings
about how to handle potentially dangerous manufacturing processes, and

motivates production
Module 20 730
Visual Factory – Footprints

! Markings on the floor or work area outlining specifically where items should
be placed or a person should stand

! Avoids employees wasting time looking for things or pondering their next
move.
! The workplace becomes clean and better organized.
! Operation on the shop floor and office become easier and safer
Module 20 731
Visual Factory – Creating Footprints

! A footprint is an outline of the items required at work areas indicating where
the items should be placed

! Mark from the floor up to workbenches etc
! Start with plastic tape to test out, then move to paint
! Color code and place legends that describe the coding
Module 20 732
Module 20 733
Reactive maintenance inherently wasteful and ineffective with following
disadvantages:
!  No warning of failure
!  Possible safety risk
!  Unscheduled downtime of machinery
!  Production loss or delay
!  Possible secondary damage
!  Real cost of reactive maintenance is more than the cost of maintenance
resources and spare parts
We need a better way!
Module 20 734
Total Productive Maintenance (TPM)
!  Both a philosophy and a set of tools
!  Used to optimize the effectiveness of manufacturing equipment and tooling
!  Starts with 5S and the Visual Factory
!  Builds a comprehensive Downtime Database
!  Predicts and prevents downtime
!  The Operator is the first point of early warning and prevention
!  Develops Professional Maintenance skills
Module 20 735
Total Productive Maintenance (TPM) dramatically
!  Reduces equipment breakdowns
!  Minimizes idle time and minor stops
!  Results in less quality defects
!  Increases productivity
!  Reduces staffing and cost
!  Lowers inventory
!  Reduces accidents
Module 20 736
Total Productive Maintenance (TPM) goals
!  To maximize overall equipment effectiveness through total employee
involvement
!  To improve equipment reliability and maintainability which, in turn, will
improve quality and raise productivity

!  To aim for maximum economy in equipment for its entire life
!  To cultivate equipment-related expertise and skills among operators
!  To create a vigorous and enthusiastic work environment
Module 20 737
6 Big Losses TPM addresses;
1. Breakdown losses due to failures and repairs
2. Setup and adjustment losses
3. Idling and minor stoppage losses
4. Speed losses
5. Scrap and rework losses
6. Start-up losses
!  1 and 2 = availability loss

!  3 and 4 = performance loss
!  5 and 6 = quality loss
Module 20 738
7 Steps of TPM
1. Initial Clean-up (5S & Visual Factory)
2. Identify and eliminate inherent faults
3. Set Initial Standards
4. General Inspection
5. Autonomous Inspection
6. Standardization
7. Autonomous Maintenance
Module 20 739
Downtime Database
!  Categorize at a minimum by Equipment, Tooling, and Change-Over
!  Segmented bar graph for E-T-O lost time
!  Subcategories for Equipment
!  Subcategories for Tooling
!  Subcategories for Other
Module 20 740
Predict and Prevent Downtime
!  Via preventative maintenance and monitoring
!  Rate/hr vs. target or historical normal output (B/W)
!  Downtime Database
!  Maintenance history
!  Statistical probability (frequency & duration)
Module 20 741
Predict and Prevent Downtime
Physical prediction of impending failure
!  Sound (bearing)
!  Temperature (cooling water)
!  Flash (core pins)
!  Shot monitoring system
!  SPC on part geometry
!  Hydraulic pressure (ejector pins)
!  Spindle loads (amps)
!  Fluids / Lubrication analysis (milipore)
!  Vibration Signature Analysis
Module 20 742
Preventive Maintenance System
!  History of downtime by major machine & tool
!  Plan PM based on frequency of failure and magnitude of average lost time
!  Have instructions, schedule/frequency & sign-off
!  Done in window of opportunity when machine is down
!  Use visual status (work completed / not completed)
Module 20 743
Role of Operator as first point of prevention and early warning
!  Provide operator awareness training
!  Create OMP (Operator - Maintenance Partnership)
!  Operator performs checks, problem solving, and improvements
Module 20 744
OMP (Operator - Maintenance Partnership)
!  Operator training in TPM
!  Operator basic equip inspection & tooling checks
!  Operator basic cleaning
!  Operator lubrication check
!  One point lessons (capture knowledge)
!  TPM Board & TPM Tags (proactive operator involvement)
Module 20 745
TPM Tags
!  Problem communication tool to and from maintenance, tool room, and
production
!  Identify abnormal machine conditions
!  Status tracking system
!  Visual management tool (hang tags)
!  TPM Tag used for recording problems & fix
!  Blue Tag-Operator or Maintenance to repair

!  Red Tag- Safety-related request (priority)
Module 20 746
The metric used to track effectiveness of TPM is called OEE or Overall
Equipment Effectiveness
!  OOE is measured as a percentage
!  OOE = Availability * Performance * Quality
!  Availability = % of scheduled production equipment is available for
production
!  Performance = % number of parts produced out of best known production
rate
!  Quality = % of good sellable parts out of total parts produced
Module 20 747
End
!  Visual Factory
!  Total Productive Maintenance (TPM)
WE WILL NOW REVIEW THE CONTROL PHASE
Module 20 748
Control Phase – Summary
!  Implement SPC and a Control
!  Verify that the process improvements have attained the goals.
!  Develop and implement the Visual Factory or TPM if relevant
!  Hand off the process to the process owners
!  Close off the project
Control Phase Summary &

Review Questions
Control Phase – Summary
Questions to ask at end of phase
!  Did we validate the measurements?
!  Did we meet the targets?
!  What risks have been identified that could jeopardize your control strategy?
!  Do we have sign-off on our changes?
!  Has proper training and documentation been provided?
!  What actions are still required to guarantee sustainability?

Review Questions
Control Phase – Review Questions
Review Question #1
A Greenbelt has used the 5S approach of Lean to set up a control method
with frequently used tools organized as shown in this graphic. The Belt has
applied the ______________ principle of 5S.
a. Shining
b. Sorting
c. Straightening
d. Sustaining

Review Questions
Review Question #1 Answer
C Straightening

Review Questions
Review Question #2
In the Control Phase a Greenbelt will identify key metrics that can be
monitored and analyzed to give an indication that a process may be moving
towards an out of spec condition. When he applies this approach he is using
__________________.
a. Poisson Derivatives
b. Inferential Statistics
c. Kanban Analysis
d. Statistical Process Control

Review Questions
D Statistical Process Control

Review Questions
Review Question #3
A Greenbelt creates for the Process Owner a Control Plan. The
________________ portion of the Control Plan details the actions to be taken
when the KPI’s indicate they may be moving outside acceptable limits.
a. Visual Factory
b. Response Plan
c. Readjustment Plan
d. Variance Tracking

Review Questions
B Response Plan

Review Questions
Module 21 Exam Review – Prep and Key Concepts
Exam Review 757

Exam Review and Key Concepts
Outline
1.  Exam Tips
2.  Key Six Sigma Concepts
Exam Review 758

!  100 Questions with 4 hours to complete
!  Pass is 80%
!  Open book
!  Your own notes are allowed, however the proctor will inspect your notes
and can reject them
!  No collections of questions and answers are allowed
!  Hand held calculators without an alphabetic keyboard are allowed. The
memory must be cleared
Exam Review 759

Exam Day
! Check your work

! Pace yourself and leave enough time to recheck your work
! Don't get hung up on one question – move on
! See if you can quickly narrow down to two possible answers
! Mine the question for clues
! Watch our for switchbacks and hedge phases
! Watch out for slang and directly quoted answers
! There is no penalty for a wrong answer, so guess if all else fails
KEEP BREATHING AND RELAX

! 
Exam Review 760

Exam Prep Tips

! Review the Six Sigma Green Belt BOK to identify key subject areas
! Buy a Six Sigma Green Belt Textbook – either the Quality Council of Indiana
CCSGB Primer or The Certified Six Sigma Green Belt Handbook by Roderick
A., Ph.D. Munro would be great
! Create or join a study group with your peers or online
! Your study schedule should review at least one chapter per week and leave
at several weeks before the exam for a combined content review.

! Read each chapter and mark key concepts or questions to pose to your
peers
! Carefully follow all the exam registration procedures .
Exam Review 761

Exam Tips
!  Understand how to use and apply each tool or concept within each chapter
!  Create hypothetical situations of where and when you could apply each
tool, or draw from previous experiences
!  Read case studies
!  After each chapter, summarize key takeaways and important topics.
Combine this list for all chapters into a master summary/cheat sheet
!  Do the practice questions. They were mostly drawn from previous exams
are are very reflective of the types of questions you will encounter
!  Use your wrong answers to focus your further studies
Exam Review 762

Exam Prep Tips
!  Create cheat sheets with formulas, key terms, tools, concepts, as well as
page number references
!  Add tabs for each chapter, or each phase of DMAIC
!  Know how your materials are organized and how to use them efficiently
!  Practice solving the problems using the calculator you plan to use on the
exam day
Exam Review 763

Exam Day
! Get a good night's sleep

! Don’t try to cram the night before the test
! Eat a well-balanced meal and stay hydrated
! Know the exact physical location of the testing site
! Give yourself plenty of time to get there
! Bring 2 current forms of ID to the testing center
! Bring plenty of pencils and your material
! A good strategy is to go through and answer all the questions you are
absolutely certain of
! Then work through the rest
! Think long thing wrong is often the case
! READ THE QUESTION
Exam Review 764

Six Sigma In 1 slide
! A quality level of 3.4 DPMO
! Y=f(X) + ε: All outcomes and results (theY) are determined by inputs (theXs)
with some degree of uncertainty

! To improve results (the Y), you have to focus on the key inputs (the Critical
Xs), modify them, and control them

! Variation is everywhere
! Valid and relevant measurements and data are required foundations for
consistent improvement
! Only a critical few inputs have significant effect on the output
! Every decision and conclusion has risk (ε) which must me weighted against
the reward
! SIPOC: Supplier, Input, Process, Output, Customer
Exam Review 765

DMAIC
Define – project charter, problem statement, scope, goals, resources,
financial, process maps
Measure – collect data, process maps, fishbone, Pareto, QFD, need
accuracy & precision
Analyze - root cause is verified, hypothesis testing (verify assumptions and
predictions regarding the relationship between process inputs and the CTQ
values)
Improve – brainstorming for ideas and solutions to problems identified in
Analyze phase
Control - project responsibilities transition from process improvement team to
operations team. Place control plan in place
Exam Review 766

!  Define phase focuses on identifying and articulating a project’s important
characteristics, including identification of the goals, objectives, and scope of
the project
!  The team members and sponsors are identified, as well as the proposed
schedule for the project
!  The desired result of the project is defined
!  The team also identifies the stakeholders, the input/output structure, and
the functions involved.
Exam Review 767

Measure Phase
The team will focus on gathering the information necessary to complete the
! 
project
First, the team will attempt to define each relevant process in great detail
! 
It will be necessary to develop a group of metrics appropriate to the

! 
processes
No metric is complete until accompanied by a measurement analysis system
! 
that identifies and quantifies any common errors in the metric

The final general objective of the measure phase is to estimate process
! 
baselines
Exam Review 768

Analyze phase
!  The team will focus on analyzing the sources of variation in the target
process
!  Based on the high-level problem, the tools to drill down with will be selected
!  This analysis may require the use of sophisticated statistical tools
!  The team will analyze the value stream. The value stream is the set of
activities that create value for the customer

!  The team will also identify the process drivers, which are the activities that
exert a significant influence on the results of processes
Exam Review 769

Improve phase
!  The first major objective of the Improve phase is to set the new process
operating conditions. These conditions are based on the experimentation

and analysis of the measure and analyze phases.
!  The next objective of the improve stage is to identify and address the failure
modes for the new processes

!  Assessing and predicting the benefits of the proposed solution also is
appropriate. Before making massive changes, the team should be able to

guess how positive the results of these solutions will be
!  The final objective of the improve stage is to implement and confirm
process improvements
Exam Review 770

Control Phase Overview
Control Phase
!  The primary objective of the Control phase is to ensure that the gains
obtained during Improve phase are maintained long after the project has
ended
!  To that end, it is necessary to standardize and document procedures, make
sure all employees are trained and communicate the project’s results
!  In addition, the project team needs to create a plan for ongoing monitoring
of the process and for reacting to any problems that arise

!  And finally close out the project
Exam Review 771

! Six Sigma uses the DPMO level of a process to generate a Sigma

! It uses the standard normal distribution as its measurement system
! A Sigma level compares the variation in process performance to the

! The higher the Sigma level the better. Six Sigma performance of 3.4
DPMO
Exam Review 772

! Six Sigma uses the DPMO level of a process to generate a Sigma
! It uses the standard normal distribution as its measurement system
! A Sigma level compares the variation in process performance to the
! The higher the Sigma level the better. Six Sigma performance of 3.4
DPMO
Exam Review 773

Basic Statistics
!  Mean (average): add all numbers in the list together and divide by the
number of items in the list
!  Median (middle): order the numbers and take the number in the middle
!  Mode: The number listed most. The most frequently observed value.
!  Variance (average distance from the average squared)
!  Standard Deviation (average distance from the average)
!  Range: The difference from the largest to the smallest value in a set
!  Confidence Intervals: estimated range of values which includes the true
value with stated probability
Exam Review 774

Normal Distribution
The normal distribution provides the basis for many statistical tools and
techniques.
•  A probability distribution where the most frequently occurring value is in
the middle and other probabilities tail off symmetrically in both
directions. This shape is sometimes called a bell-shaped curve
•  Curve theoretically does not reach zero; thus the sum of all finite areas
total less than 100%
•  Curve is symmetric on either side of the most frequently occurring value
•  The peak of the curve represents the center, or mean, of the process
•  For practical purposes, the area under the curve represents virtually
100% of the variation the process is capable of producing
Exam Review 775

Z-Value
!  A data point's position between the mean and another location (usually
mean) as measured by the number of standard deviations
!  A measure of process capability and corresponds to the process sigma
value that is reported
Exam Review 776

Statistical Error
!  Type 1, Alpha or α errors: also known as an "error of the first kind", an α
error, or a "false positive": the error of rejecting a null hypothesis when it is
actually true
!  Type 2, Beta or β errors: also known as an "error of the second kind", a
β error, or a "false negative": the error of failing to reject a null hypothesis
when it is in fact not true
Exam Review 777

Hypothesis Testing
!  Tells us if a statistical parameter (average, standard deviation, etc.) is
different from a value of interest
!  Hypothesis takes the form Ho: µ = a target or known value
!  Practical Difference: The difference which results in an improvement of

practical or economic value to the company. Reflects the VOB
!  Statistical Difference: A difference or change to the process that
probably (with some defined degree of confidence) did not happen by
chance. Reflects the VOC
Exam Review 778

Multi-Vari plots
! Are effective tools for assessing the variation within samples or within
particular parts.
! Multi-Vari plots can be used to analyze variation over time or between
different batches
! Primarily used to isolate the causes of variation and to obtain more
information about the interactions among factors

! Identifies possible X s or families of variation. These families of variation can
hide within a subgroup, between subgroups or over time

! Helps screen X s by visualizing three primary sources of variation. Later we
will perform Hypothesis Tests based on the findings
Exam Review 779

Correlation Co-efficient
!  Typically denoted by r) is a measure of the correlation between two
variables X and Y, giving a value between +1 and −1
!  A value of 1 implies that the relationship between X and Y is perfect, with
all data points lying on a line for which Y increases as X increases
!  A value of −1 implies that all data points lie on a line for which Y decreases
as X increases
!  A value of 0 implies that there is no linear relationship between the
variables
Exam Review 780

Central Limit Theorem (CLT)
!  States conditions under which the sum of a sufficiently large number of
independent random variables each with finite mean and variance, will be
approximately normally distributed
Exam Review 781

Common Charts
!  Pareto Chart: A Pareto chart is a bar chart ordered from category with the
highest value to category with the lowest value
!  Also shows cumulative values in a line.
!  Commonly used to show which areas to focus on
Exam Review 782

Common Charts
Box Plots: aka Box & Whisker diagrams, show distributions with:
!  The median
!  A box around the middle 50% of the range of values (interquartile)
!  Tails showing the bottom 25% of values, and the top 25% of values
Exam Review 783

Sampling
Random Sampling: items are selected randomly from the entire population
Stratified Sampling: Stratified Sampling is when the population is dived into

non-overlapping subgroups or strata and a random sample is taken from
each subgroup
Exam Review 784

MSA (Measurement System Analysis): seeks to identify the components of
variation in the measurement. Common tools are ANOVA and Gage R+R
Goal is to measure the amount of variability induced in measurements that
comes from the measurement system itself and compares it to the total
variability observed to determine the viability of the measurement system
Key measures: Repeatability and Reproducibility, Precision, Linearity, and

Stability
Exam Review 785

ANOVA
!  Used for hypothesis testing when comparing multiple groups.
!  Hypothesis takes the form Ho: µ1 = µ2 = µ3 = …
!  Tests whether the means of several groups are all equal, and therefore
generalizes Student's two-sample t-test to more than two groups
!  The observed variance is partitioned into components due to different
explanatory variables
Exam Review 786

DOE Design Of Experiments
Uses statistical tools, such as ANOVA above and regression, to be able to
determine the importance of different factors with a minimal amount of
data. It is used when you have many different factors that may impact
results (i.e.: many x’s that impact Y in the classic Y=f(x) formula)
Exam Review 787

Linear Regression
!  Linear regression attempts to use a straight line to determine a formula for
a variable (y) from one or more factors (Xs)
!  linear regression can be used to fit a predictive model to an observed data
set of y and X values
!  We quantify the strength of the relationship between y and the Xj, to assess
which Xj may have no relationship with y at all, and to identify which subsets
of the Xj contain redundant information about y
Exam Review 788

Non-Normal Distribution
First determine if the data is normal. If it is not: consider how it will effect the
tools you plan to use; e.g. DOE, ANOVA and t-tests assume normality
Exam Review 789

Variation
Common Cause - causes of variation that are inherent in a process over
time. They affect every outcome
!  Common cause variation inside control limits - do NOT adjust process
Special Cause - relatively large, unusual variation usually comes from

outside the process
Exam Review 790

Sources of Variation
Within Unit or Positional
–  Within piece variation related to the geometry of the part.
–  Variation across a single unit containing many individual parts such
as a wafer containing many computer processors.
–  Location in a batch process such as plating.
Between Unit or Cyclical

–  Variation among consecutive pieces.
–  Variation among groups of pieces.
•  Variation among consecutive batches.
Temporal or over Shift-to-Shift

–  Day-to-Day
–  Week-to-Week
Exam Review 791

791
Key Metrics
Rolled Throughput Yield: Calculate the yield (number out of step/number
into step) of each step. Multiply these together
Defects Per Million Opportunities (DPMO): Number of defects divided by

number of opportunities multiplied by one million
Exam Review 792

Lean Concepts
!  VSM Value Stream Mapping: is a tool used to understand a process and
how much value-added and non-value added time is spent on and between
each activity. The VSM will include a data box of key statistics
Exam Review 793

Lean Concepts
!  TAKT Time: Rate of customer demand. Effective Working Time / Average
Customer Demand
!  Batch Size: Reducing batch sizes generally reduces cycle time and
improves throughput
!  Lead Time - The average time it takes for one unit to go through the entire
process including time waiting between sub-processes (aka throughput time
or turnaround time
Exam Review 794

Lean Concept
The 7 Wastes (Muda)
1. Overproduction
2. Waiting
3. Transporting
4. Overprocessing
5. Excess Inventory
6. Excess Motion
7. Defects
Exam Review 795

Lean Concepts
Kaizen;
!  Kaizen is a philosophy of continuous improvement
!  Improvements are based on the insights and experiences of lower-level
employees, as opposed to the traditional executive-driven Western model

!  Can be successful only with adequate training, defined operating practices,
and buy-in from all employees

!  Constant communication exists
!  Focus is small improvements, not breakthrough changes
!  Driven from the bottom-up
!  Based on the premise that the people who do the work know it best
Exam Review 796

Lean Concept
Kanban
! Kanban is faster, more efficient, and saves significant money over most other
production models
! Reduces inventory, on average, by 25 to 75%
! The visually organized environment ensures all parts are easily found and
continually stocked
! The speed of moving from one task to another is significantly reduced by the
creation of clearly marked flow lanes, kanban cards, and clearly marked
labels
Exam Review 797

Lean Concepts
Kaizen Blitz (aka Kaizen Event)
!  Whereas Kaizen focuses on making small, evolutionary changes, a Kaizen
blitz focuses on making a rapid improvement in a manner of days (usually

5), though planning can take longer
!  Executed by a team assembled for the purpose
!  Primary vehicle for change in organizations implementing Lean
Exam Review 798

Lean Concepts
!  Queue Time - The time between sub-processes that the item gets
moved or sits around waiting for someone to work on it (aka

Waiting and Transportation Time or Inventory/Transportation Time
!  Value Add Time - Time for those process steps that actually value
to the item (aka Value Creating Time)

!  Cycle Time (CT) - The average time between completed units
coming out the end of the process

!  Velocity - in Lean, is a metric that indicates the rate at which value
is added during a process phase
Exam Review 799

799
Setup Time
! Setup time is the interval between the completion of the last item and the
beginning of the next item. Consists of four components:

!  Preparation - the set of tasks necessary to gather all of the
materials and people for the activity
!  Replacement - the set of tasks required to adjust and reconfigure
equipment before the next item can be processed
!  Location - the positioning or moving tasks that must be completed
between iterations of a process
!  Adjustment - the set of monitoring or fine-tuning tasks that must
be performed between iterations to ensure correct performance of
a process
Exam Review 800

Spaghetti Diagram;
! Used to track motion of a person, item, or activity related to a process via
continuous flow lines

! Identifies redundancies in the work flow and opportunities to expedite
process flow
! Also highlights major intersection points; these point are causes of delay
! Helps one see waste that would be otherwise overlooked.
! Like Value Stream maps, one can create current state and future state
diagrams
Exam Review 801

Lean Concepts
SMED (Singe Minute Exchange of Dies): covers the techniques for
obtaining a changeover time of less than 10 minutes. Consists of 6 steps:
Observe the current changeover process
!  Identify internal and external activities
!  Convert activities from internal to external setup
!  Increase efficiency of the remaining internal activities
!  Optimize the Startup time
!  Increase efficiency of external activities
Exam Review 802

Lean Concepts
Theory of Constraints: based on the premise that the goal achievement is
limited by at least one constraining process. Only by increasing flow
through the constraint can overall throughput be increased
Exam Review 803

Lean Concepts
TPM (Total Productive Maintenance): a program for planning and achieving
minimal machine downtime: 7 Steps of TPM
!  Initial Clean-up (5S & Visual Factory)
!  Identify and eliminate inherent faults
!  Set Initial Standards
!  General Inspection
!  Autonomous Inspection
!  Standardization
!  Autonomous Maintenance
The metric used in Total Productive Maintenance environments is called OEE

or Overall Equipment Effectiveness
Exam Review 804

Lean Concepts
5Ss
1.  Sort
2.  Straighten or Streamline
3.  Shine
4.  Standardize
5.  Sustain
Exam Review 805

Lean Concepts
Visual Management uses;
!  Floor and surface marking
!  Shadow boxes
!  Samples
!  Visual indicators
!  Obstacle height limits
!  Lights and sounds
!  Arrows, zones, stickers
!  Scoreboards
!  Labels and tags
Exam Review 806

Lean Concepts
Visual Factory
!  Describes visual methods a manufacturing plant can use to communicate
information about a process to everyone who needs to understand it as

they work
!  Use of visual tools will convey information in a clear, accurate, efficient, and
organized way to those who need to know it

!  Overall goal is to make the control and management of a company as
simple as possible
!  Visual Factory is implemented in two stages;
!  Determining what information needs to be communicated

!  How this information will be communicated
Exam Review 807

Lean Concepts
Standard Work
!  Standard work is one of the most powerful but least used lean tool
!  By documenting the current best practice, standard work forms the baseline
for Kaizen
!  As the standard is improved, the new standard becomes the baseline for
further improvements
!  Each step in the process should be defined and must be performed
repeatedly in the same manner

!  Any variations in the process will most likely increase cycle time and cause
quality issues
Exam Review 808

Lean Concepts
Poka-Yoke - Error-Proofing ;
! Poka-yoke states that preventing errors is better than detecting them as
rework is a non-value-added activity

Processes must be rigorously analyzed and improved so the frequency and
! 
severity of mistakes is reduced

Options for error-proofing include; auto-correcting systems, auto-shutdown,
! 
jigs, digital counters, and warning systems
Exam Review 809

Lean Concepts
Pull
! Increases throughput
! By pulling material in small lots, inventory cushions are removed, exposing
problems and emphasizing continual improvement

! Manufacturing cycle time is reduced
! Ideal situation is to have lot sizes of one pulled from one process to the next
! Lot sizes can be reduced by;
!  Improving material handling

!  Reducing setup times
!  Reducing setup costs
Exam Review 810

Lean Concepts
Continuous Flow
!  The creation, ordering, and provision of any good or any service can be
made to flow
!  Think about ways to;
!  Line up all of the essential steps needed to get a job done

!  Obtain a steady, continuous flow
!  No wasted motions
!  No interruptions
!  No batches or queues
!  Focus on the actual object or service
!  Ignore traditional boundaries
Exam Review 811

Lean Concepts
Level Loading
!  Its purpose is to regulate and moderate the flow of orders in a particular

process. Level loading typically is performed during the improve stage
!  Can be used to reduce the need for inventory checks during a process
!  Before it can be implemented, protocols must be standardized and
employees must be trained
!  The intention is to eliminate wait time at the beginning of a given process
!  Therefore, each completed unit should begin the next phase of the
production process immediately
Exam Review 812

FMEA (Failure Mode and Effects Analysis):
!  Helps determine where to focus improvement efforts by analyzing severity
of failures, probability of occurrence of an error, and likelihood of detection
of an error
!  RPN (Risk Priority Number) is computed by multiplying Occurrence,
Severity, and Detectability together. The highest RPNs should be
addressed first
Exam Review 813

Attribute (Discrete) vs. Variable Data:
!  Discrete or Attribute data is considered the same thing. Discrete data is
any data not quantified on an infinitely divisible numerical scale. Discrete
data has boundaries and includes any number that must be an integer
!  Variable or Continuous data is any data on a continuous scale. Examples
include length, diameter, temperature, weight, time
Exam Review 814

Control Charts
Attribute Data Control Charts
!  Attribute data - qualitative data that can be counted for recording and
analysis good/bad, yes/no
!  the average and dispersion are closely related; therefore, only one chart
needed
!  P-Chart – proportions percent defective with variable or constant sample
size
!  NP-chart– number of defects with constant sample size
!  C-Chart – count of defects with constant sample size
!  U-Chart – defects per unit with variable or constant sample size
Exam Review 815

Control Charts
Variable Data Control Charts
!  Variable data – measured - two types (Discrete) count data and
(Continuous) data
!  X and MR
!  X-bar and Range
!  X-bar and S (standard deviation)
Exam Review 816

Voice of the Customer (VOC): You can not exit the Define phase without an
understanding of what’s important to the customer
! Only process that add value to the customer are value-add processes. You
need to understand the customer to know what is value-add

! In control charts the VOC is translated to Upper Spec Limit (USL) & Lower
Spec Limit (LSL)
Exam Review 817

Critical to Quality (CTQ)
! Represent the product or service characteristics that are defined by the
customer (internal or external)

! May include the upper and lower specification limits or any other factors
related to the product or service
Exam Review 818

COPQ (Cost Of Poor Quality)
!  Rework cost = Defect rate x # Units x Cost of rework per unit
!  Penalty from not performing work correctly the first time or not meeting
customer’s expectation
!  cost categories = appraisal, internal failure, prevention, external failure
Exam Review 819

QFD (Quality function deployment)
! Method to transform user demands (VOC) into design quality, to deploy the
functions forming quality, and to deploy methods for achieving the design
quality into subsystems and component parts, and ultimately to specific
elements of the manufacturing process
! QFD Steps:
!  Understand Customer and Technical Requirements

!  Translate Technical Requirements to Critical to Quality
Characteristics (CTQs)
!  Build to those CTQs
Exam Review 820

House of Quality
Exam Review 821

Root Cause Analysis
! Use cause and effect diagrams,5 Whys, relational matrices, and other
problem-solving tools to identify the true cause of a problem
! Derivative of FMEA
! It is not the initial response to the problem
! Nor is it a restatement of the findings
! Usually the root cause is a process, procedure or organizational failure
Exam Review 822

Cause and Effect Diagram (Fishbone or Ishikawa)
!  Used to identify and organize potential root causes
!  Problem solving analysis done by brainstorming
!  Common categories - Measurement, Materials, People, Process,
Equipment, Environment
!  Have detailed problem statement at head of the fish - “effect”
Exam Review 823

Control Limits: are the ‘voice of the process’ and based on the standard
deviation and variability of the process
Control plan: the plan used to control the process. Itis used in the Control
phase & after project closure to ensure project improvements are sustained
! What needs to be captured is what is being measured; how it is used, what
sampling method is used, who owns the control chart, where it is located, and
what conditions constitute loss of control or improvement that require
corrective action
! Usually Cp, Cpk, Pp, and Ppk are measured as part of the control plan, and
in the process control charts
Exam Review 824

Process Capability: Measures the capability of a process to meet customer
specifications
!  The higher the Cp, Cpk, Pp, or Ppk, the better, as the less variance there is
in the process
Short-Term Capability indices (Cp Cpk): Uses short term process variation
to determine process capability. Use when no long-term data available
Long Term Capability indices (Pk Ppk):Uses long-term process standard

variation. Use when long-term data is available
Exam Review 825

Six Sigma PDF

Uploaded by

Copyright:

Available Formats

Six Sigma PDF

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Six Sigma PDF

Uploaded by

Copyright:

Available Formats

What is a Six Sigma Green Belt and their role?

What is a Six Sigma Green Belt and their role?

What does the ASQ Green Belt certification exam entail?

What does the ASQ Green Belt certification exam entail?

Six Sigma Green Belt Certification

Module 0 – Certification Exam and Course Overview

2. Lean Principles in the Organization

3. Design for Six Sigma (DFSS)

4. How processes, inputs, outputs, and feedback affect the organization.

Extolled the benefits of doing things right the first time

Four cardinal rules of quality management:

1. the performance standard should be set as zero defects;

1. Maintain consistent purposes 8. Eliminate fear

2. Adapt a new philosophy 9. Reduce interdepartmental barriers

5. Constant quality improvement 12. Promote employee pride

7. Establish leadership Module 1 21

some degree of uncertainty (ε)

them, and control them

is to find it and minimize it!

context of the decision

Competitive Advantage is gained by meeting customer expectations

Strong alignment to organizational goals

will yield significant returns.

analysis and the application of specific variance-reduction techniques

process and financial performance

All roads lead back to the concept of the Cost of Quality

There are widely-used financial metrics as well as balanced scorecards

Six Sigma also provides us with a set of key metrics

DPO – Defects Per Opportunity

DPMO – Defects Per Million Opportunities

FTY – First Pass Yield

TPY – Throughput Yield

RTY – Rolled Throughput Yield

To be covered in detail later in the course

Return on Assets (ROA) = Net Income /Average Total Assets

value (PV). Then they are summed to give the NPV.

Lagging and leading measures

Across the following four areas:

do everything it can to minimize inventory

Value-Added vs. Non-Value-Added Activities;

valuable product or service to its customers

not add value

activities thus improving the value chain

value-added, then addressing the non-value-added activities include; Process Cycle

! Even the smoothest process has constraints

! Improvement efforts are devoted to improving performance by removing or reducing

constraints without sacrificing quality elsewhere

maximizing the potential of the constrained area

Value-Added vs. Non-Value-Added Activities;

Examples of non-value added activities include;

limited areas of a process

materials and resources when a subsequent activity is 'demanding' the process be

waste and streamlining processes, an organization can approach perfection

Process Cycle Efficiency Metric;

of times the process is completed in an hour

1. Design for Six Sigma (DFSS)

Do the plan (executes),

Check the results,

action or improvement that should be pursued

1.  the performance standard should be set as zero defects;

!  Even the smoothest process has constraints

!  Improvement efforts are devoted to improving performance by removing or reducing

1. Design for Six Sigma (DFSS)

!  Used to uncover potential failures that can:

2.  Lean Principles in the Organization

3.  Design for Six Sigma (DFSS)

!  The Define phase focuses on identifying and articulating a project’s