Descriptive Statsistics

Statistical Methods for Decision Making
[email protected]
4YS9XLK8G2
What do the numbers tell?
This file is meant for personal use by [email protected] only.

Proprietary content. Sharing
©GreatorLearning. All contents
publishing the Rights Reserved.
in part or fullUnauthorized
is liable for legaluse or distribution
action. prohibited.
Why Study Statistics
• Technological developments, Revolution of Internet and social
networks, data generated from electronic devices, produce large
amount of data
• Large storage capacity
[email protected]
4YS9XLK8G2
• Advancement in enormous computing power to effectively process

and analyze large amount of data
• Better data visualization from Business Intelligence
• Discovery of patterns and trends from this data can help
organizations gain competitive advantage in marketplace

action. prohibited.
Types of Statistics
• Descriptive statistics is concerned with Data Summarization
Graphs/Charts and tables.
• Inferential Statistics is the method used to talk about a

[email protected]
4YS9XLK8G2
population parameter from a sample. It involves point

estimation, interval estimation, and hypothesis testing.

action. prohibited.
Some Key Terms
• Population is the collection of • Parameter is the population characteristic
all possible observations of a of interest. For example, you are interested
specified of characteristic in the average income of a particular class
interest. of people. The average income of this
[email protected]
entire class of people is called a parameter.
4YS9XLK8G2
• Sample is a subset of • Statistic is based on a sample to make

population inferences about the population
parameter. The average income in of
population can be estimated by the
average income based on the sample. This
sample average is called a statistic.
action. prohibited.
Types of Data
Data
[email protected]
Categorical Numerical
4YS9XLK8G2
(Qualitative) (Quantitative)
E.g. Gender, Location of
store, Preference
Discrete Continuous
E.g. Family size, Number of E.g. Waiting time, Length of
rooms in a hotel, number of a part produced
credit cards issued

action. prohibited.
Measurement Scales
• Nominal –e.g. Internet service provider
• Ordinal: e.g. Bond rating, employee designation

[email protected]
4YS9XLK8G2
• Interval: e.g. IQ Score, Temperature in °C or °F
• Ratio: e.g. cost of an item

action. prohibited.
Measure of central Tendency
• You need the summary measures of central tendency to
draw meaningful conclusions in the functional area of
operation.
[email protected]
4YS9XLK8G2
The most widely used measures of central tendency are the

Arithmetic Mean, Median and Mode.

action. prohibited.
Arithmetic Mean
• Arithmetic mean(called Mean) is defined as the sum of all
observations in a data set divided by the total number of
observations. For example, consider a data set containing
the following observations:
[email protected]
4YS9XLK8G2
• In symbolic form mean is given b

action. prohibited.
Arithmetic Mean - Example
• The inner diameter of a particular grade of tire based on 5 sample
measurements are as follows: (Figures in millimetres)
565, 570, 572, 568, 585

[email protected]
4YS9XLK8G2
Applying the formula
We get mean = (565 + 570+572+568+585)/5 =572
• Caution: Arithmetic Mean is affected by extreme values or fluctuations

in sampling. It is not the best average to use when the data set contains
extreme values (Very high or very low values).
action. prohibited.
Median
• Median is the middle most observation when you arrange

data in ascending order of magnitude. Median is such 50% of
the observations are above the median and 50% of the
[email protected]
observations are below the median.

4YS9XLK8G2
• Median is a very useful measure for ranked data in the

context Preferences and rating. It is not affected by extreme
values (greater resistance to outliers)
• Median = (n+1)/2 th value of ranked data.
• n = Number of observations in the sample This file is meant for personal use by [email protected] only.
action. prohibited.
Median - Example
• Marks obtained by 7 students in computer science exam

are given below: Compute the median.
45 40 60 80 90 65 55
[email protected]
4YS9XLK8G2
• Arranging the data after ranking them

40 45 55 60 65 80 90
• Median = (n+1)/2 th value in this set = (7+1)/2 th
observation= 4th observation=60
• Hence median = 60 for this problem.
action. prohibited.
[email protected]
4YS9XLK8G2
https://economictimes.indiatimes.com/articleshow/52450273.cms?utm_source=contentofinterest
&utm_medium=text&utm_campaign=cppst
Sharing or publishing the contents in part or full is liable for legal action.
US median household income climbs to new high
If you're a member of the middle class, chances are things are looking up. Median
household income reached a record $61,372 in 2017, up 1.8 percent from $60,309
in 2016.This marks the third year in a row that median household income has
gone up, according to the U.S. Census Bureau, which compiled the data.
[email protected]
4YS9XLK8G2
https://www.cnbc.com/2018/09/12/median-household-income-climbs-to-new-high-
of-61372.html

action. prohibited.
Questions about the response time of ambulances dispatched to the stadium
were also raised. The head of New South Wales Ambulance was to be hauled
before the state health minister Jillian Skinner on Thursday after the ambulance
authority issued conflicting statements about their response times. The arrival of
[email protected]
4YS9XLK8G2
the first ambulance took 15 minutes, NSW Ambulance clarified in a statement on

Wednesday. The state's median response time for the highest priority life-
threatening cases was just under eight minutes in 2013-14, according the
authority's statistics
http://timesofindia.indiatimes.com/articleshow/45292785.cms?utm_source=conte
ntofinterest&utm_medium=text&utm_campaign=cppst

action. prohibited.
Mode
• Mode is that value which occurs most often. It has the
maximum frequency of occurrence. Mode also has
resistance to outliers.
• Mode is a very useful measure when you want to keep in the
[email protected]
4YS9XLK8G2
inventory, the most popular shirt in terms of collar size

during festival season.
• Caution: In a few problems in real life, there will be more
than one mode such as bimodal and multi-modal values. In
these cases mode cannot be uniquely determined.
action. prohibited.
Mode - Example
• The life in number of hours of 10 flashlight batteries are

as follows: Find the mode
[email protected]
4YS9XLK8G2
• 340 340 350 350 340 340 320 340 330 330
• 340 occurs five times. Hence, mode = 34O.

action. prohibited.
Comparison of Mean, Median
and Mode
Mean Median Mode
Affected by extreme values. Not affected by extreme values. Not affected by extreme values.
Can be treated algebraically. That is, Cannot be treated algebraically. That

[email protected]
Cannot be treated algebraically.
4YS9XLK8G2 Means of several groups can be is, Medians of several groups cannot That is, Modes of several groups
combined. be combined. cannot be combined.

action. prohibited.
Measures of Dispersion
• In simple terms, of dispersion indicate how large the spread

of the distribution is around the central tendency.
• It answers unambiguously the equation
[email protected]
“What is the magnitude of departure from the average value

4YS9XLK8G2
for different groups having identical averages?”

action. prohibited.
Range
• Range is the simplest of all the measures of dispersion. It is
calculated as the difference between maximum and
minimum value in the data set.
[email protected]
4YS9XLK8G2
Range = X Maximum –X Minimum

action. prohibited.
Range -Example
Example for calculating Range

The following data represents the percentage return on the
investment for the 10 mutual funds per annum.
Calculate the Range.
[email protected]
4YS9XLK8G2
12, 14, 11, 18, 11.3, 12, 14, 11, 9
Range = X Maximum –X minimum = 18 - 9 = 9

Caution: If one of the components of range namely the
maximum value or minimum value becomes an extreme value,
then range should not be used. This file is meant for personal use by [email protected] only.
action. prohibited.
Inter-Quartile Range(IQR)
• IQR= Range computed on middle 50% of the observations

after eliminating the highest and lowest 25% of observations
in a data set that is arranged ascending order. IQR is less
affected by outliers.
[email protected]
4YS9XLK8G2
• IQR =Q3-Q1

action. prohibited.
Interquartile Range-Example
• The following data represents the percentage return on

investment for 9 mutual funds per annum. Calculate
interquartile range.
[email protected]
4YS9XLK8G2
• Data set: 12, 14, 11, 18, 11.5, 12, 14, 11, 9
• Arranging in ascending order, the data set becomes
9, 11, 11, 11.5, 12, 12, 14, 14, 18
IQR = Q3 – Q1 = 14 – 11 = 3
action. prohibited.
Standard deviation
• Standard deviation forms the cornerstone for the inferential
statistics.
• To define standard deviation, you need to define another

[email protected]
4YS9XLK8G2
term called variance. In simple terms, standard deviation is

the square root of variance.

action. prohibited.
[email protected]
4YS9XLK8G2

action. prohibited.
Example of Standard Deviation
• The following data represent the percentage return on
investment for 10 mutual funds per annum. Calculate the
sample standard deviation.
[email protected]
4YS9XLK8G2
• 12, 14, 11, 18, 10.5, 11.3, 12, 14, 11, 9

action. prohibited.
[email protected]
4YS9XLK8G2

action. prohibited.
Solution for the example cont.
Form the spreadsheet of the Microsoft excel in the previous slide, it is
easy to see
that Mean = = 12.28 ( In column A and row14, 12.28 is seen)
[email protected]
4YS9XLK8G2
Sample variance = = 6.33 ( In column D and row14, 6.33 is seen)
Sample standard deviation = = 2.52 ( In column D and row15,

2.52 is seen)

action. prohibited.
[email protected]
4YS9XLK8G2
Histogram( also known as frequency histogram) is a snap shot of the frequency distribution.
Histogram is a graphical representation of the frequency distribution in which the X-axis represents the
classes and the Y-axis represents the frequencies in bars.
Histogram depicts the pattern of the distribution emerging from the characteristic being measured.

action. prohibited.
The Empirical Rule
• The empirical rule approximates the variation of data in the
bell-shaped distribution.
• Approximately 68% of the data in a bell shaped distribution is
within 1 standard deviation of the mean or
[email protected]
4YS9XLK8G2

action. prohibited.
The Empirical Rule
• Approximately 95% of the data is a bell-shaped distribution lies within
two standard deviations of the mean, or
• Approximately 99.73% of the data is a bell-shaped distribution lies

[email protected]
4YS9XLK8G2
within three standard deviations of the mean, or

action. prohibited.
Coefficient of Variation
(Relative Dispersion)
• Coefficient Variation (CV) is defined as the ratio of standard
deviation to mean.
[email protected]
• In symbolic form
4YS9XLK8G2
CV = S/𝑋ത for the sample data and = σ/µ for the population
data.

action. prohibited.
Example
• Following is the performance of two Sales Teams in terms
of monthly sales
Comment on the results.
[email protected]
4YS9XLK8G2
Sales Team 1
• Standard deviation: 10 units
Sales Team 2
• Standard Deviation 12 units
action. prohibited.
Example
• Additional information
Sales Team 1
• Mean: 70 units
[email protected]
4YS9XLK8G2
Sales Team 2
• Mean: 120 units

action. prohibited.
Interpretation for the Example
• The CV for Team 1 is 10/70 = 0.14 or 14%
• The CV for Team 2 is 12/120 = 0.10 or 10%
[email protected]
4YS9XLK8G2

action. prohibited.
The five number summary
• The five numbers that help describe the center, spread and
shape of the data are:
▪ XSmallest
▪
[email protected]
4YS9XLK8G2
First Quartile (Q1)
▪ Median (Q2)
▪ Third Quartile (Q3)
▪ XLargest

action. prohibited.
CASE STUDY - HEALTH INSURANCE
• Most companies are now recognizing the power of data in making crucial
business decisions. For an Insurance company, it becomes more important to
study various attributes about their customers. Leveraging this customer
information to make business decisions can provide a competitive edge to the
company over other players in the market
[email protected]
4YS9XLK8G2
• We are provided with some customer data of an Insurance company like age,
gender, BMI and medical charges billed by insurance company. We need to
explore this data to see if we can derive some meaningful insights from this data.

action. prohibited.
[email protected]
4YS9XLK8G2

action. prohibited.
Five number summary and
The Boxplot
• The Boxplot: A graphical display of the data on the five-
number summary:
[email protected]
4YS9XLK8G2

action. prohibited.
Five number summary:
Shape of Boxplots
• If data is symmetric around the median then the box and
central line are centered between the endpoints.
[email protected]
4YS9XLK8G2
• A Boxplot can be shown in either a vertical or horizontal

orientation.
action. prohibited.
Distribution shape and
The Boxplots
[email protected]
4YS9XLK8G2

action. prohibited.
Boxplot Example
• Below is a Boxplot for the following data:
[email protected]
4YS9XLK8G2
• The data are right skewed, as the plot depicts

Sharing or publishing the contents in part or full is liable for legal action.
Boxplot example showing an outlier
• The Boxplot below of the same data shows the outlier
value of 27 plotted separately.
• A value is considered an outlier if it is more than 1.5 times
[email protected]
4YS9XLK8G2
the interquartile range between Q1 or above Q3.

action. prohibited.
Covariance
• The covariance measures the strength of the linear relationship between two
numerical variables (X and Y). Formula for sample Covariance is
[email protected]
4YS9XLK8G2
• Drawback of covariance: It can have any value, so it cannot be used to

determine the relative strength of the relationship

action. prohibited.
Coefficient of Correlation
• Coefficient of correlation (r) measures the relative strength of a linear
relationship between two numerical variables.
[email protected]
• The values r range from -1 to + 1

4YS9XLK8G2
• The value -1 indicates a perfect negative correlation and +1 indicates a perfect

positive correlation

action. prohibited.

Descriptive Statsistics

Uploaded by

Copyright:

Available Formats

Descriptive Statsistics

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

Descriptive Statsistics

Uploaded by

Copyright:

Available Formats

Statistical Methods for Decision Making

This file is meant for personal use by [email protected] only.

• Advancement in enormous computing power to effectively process

This file is meant for personal use by [email protected] only.

• Inferential Statistics is the method used to talk about a

population parameter from a sample. It involves point

This file is meant for personal use by [email protected] only.

• Sample is a subset of • Statistic is based on a sample to make

This file is meant for personal use by [email protected] only.

• Ordinal: e.g. Bond rating, employee designation

• Interval: e.g. IQ Score, Temperature in °C or °F

• Ratio: e.g. cost of an item

This file is meant for personal use by [email protected] only.

The most widely used measures of central tendency are the

This file is meant for personal use by [email protected] only.

• In symbolic form mean is given b

This file is meant for personal use by [email protected] only.

565, 570, 572, 568, 585

Applying the formula

We get mean = (565 + 570+572+568+585)/5 =572

• Caution: Arithmetic Mean is affected by extreme values or fluctuations

• Median is the middle most observation when you arrange

observations are below the median.

• Median is a very useful measure for ranked data in the

• Marks obtained by 7 students in computer science exam

• Arranging the data after ranking them

This file is meant for personal use by [email protected] only.

the first ambulance took 15 minutes, NSW Ambulance clarified in a statement on

This file is meant for personal use by [email protected] only.

inventory, the most popular shirt in terms of collar size

• The life in number of hours of 10 flashlight batteries are

• 340 occurs five times. Hence, mode = 34O.

This file is meant for personal use by [email protected] only.

Can be treated algebraically. That is, Cannot be treated algebraically. That

This file is meant for personal use by [email protected] only.

• In simple terms, of dispersion indicate how large the spread

“What is the magnitude of departure from the average value

for different groups having identical averages?”

This file is meant for personal use by [email protected] only.

Range = X Maximum –X Minimum

This file is meant for personal use by [email protected] only.

Example for calculating Range

12, 14, 11, 18, 11.3, 12, 14, 11, 9

Range = X Maximum –X minimum = 18 - 9 = 9

• IQR= Range computed on middle 50% of the observations

This file is meant for personal use by [email protected] only.

• The following data represents the percentage return on

• To define standard deviation, you need to define another

term called variance. In simple terms, standard deviation is

This file is meant for personal use by [email protected] only.

This file is meant for personal use by [email protected] only.

• 12, 14, 11, 18, 10.5, 11.3, 12, 14, 11, 9

This file is meant for personal use by [email protected] only.

This file is meant for personal use by [email protected] only.

Sample variance = = 6.33 ( In column D and row14, 6.33 is seen)

Sample standard deviation = = 2.52 ( In column D and row15,

This file is meant for personal use by [email protected] only.

This file is meant for personal use by [email protected] only.

This file is meant for personal use by [email protected] only.