Module-2 (9

Hours)Business
Research Design

•Module-2 (9 Hours)Business Research

Design: Meaning, types and significance of
research design, errors affecting research
design.
•Exploratory Research: Meaning, purpose,
methods, Literature search, experience
survey, focus groups and comprehensive case
methods.
•Conclusive Research Design: Descriptive
Research, Meaning, Types, Cross sectional
studies and longitudinal studies.
•Experimental Research Design: Meaning
and classification of experimental designs,
formal and informal, Pre experimental
design, True experimental design, Quasi-
experimental design, Statistical experimental
design.
 What is Research Design ?

• When a research is carried-out, it follows a definite pattern or plan of

action throughout the procedure, i.e., since the problem identification
to the report preparation and presentation.
• This definite pattern or plan of action is called "research design". It is a
map that guides the researcher in collecting and analyzing the data. In
other words, research design acts as a blueprint that is followed
throughout the research work.
• Definition of Research Design

According to William Zikmund :

"Research design is defined as a master plan specifying the methods and
procedures for collection and analyzing the needed information."
 Reduces Cost :
• Research design is needed to reduce the excessive costs in
terms of time, money and effort by planning the research
work in advance

Facilitate the Smooth Scaling :

Significance • In order to perform the process of scaling smoothly, an

of research efficient research design is of utmost importance. It makes

the research process effective enough to give maximum
relevant outcome in an easy way.
design Helps in Relevant Data Collection and Analysis :
• Research design helps the researchers in planning the
methods of data collection and analysis as per the
objective of research. It is also responsible for the reliable
research work as it is the foundation for entire research.
Lack of proper attention in preparation of research design
can harm the entire research work.
4) Assists in Smooth Flow of Research
Operations :
• Research design is necessary to give better and effective
structure to the research. Since all the decisions are made
in advance, therefore, research design facilitates the
smooth flow of research operations and reduces the
possible problems of researchers.

5) Helps in Getting Reviews from Experts :

• Research design helps in developing an overview about the
whole research process and thus assists in getting
responses and reviews from different experts in that field.

6) Provides a Direction to Executives :

• Research design directs the researcher as well as the
executives involved in the research for giving their relevant
assistance
 • Sampling Errors
• Sampling Bias: When the sample is not representative of
the target population.
• Non-Response Bias: When individuals in the sample
refuse to participate or are unable to be contacted.
• Frame Error: When the sampling frame (list of individuals
or elements from which the sample is drawn) is
incomplete or inaccurate.
Errors • Measurement Errors
• Systematic Error: A consistent error that occurs in the
Affecting same direction.
• Random Error: An error that occurs due to chance and is
Research not consistent.
• Observer Bias: When the researcher's subjective
Design judgment influences the observation or recording of data.
• Instrument Bias: When the measuring instrument is
flawed or inaccurate.
• Experimental Errors
• Confounding Variables: Variables that are not controlled
for and can influence the outcome of the study.
• Placebo Effect: When participants' expectations or beliefs
influence their responses.
• Hawthorne Effect: When participants' behavior changes
because they know they are being observed.
• Other Errors
• Population Specification Error: When the researcher fails to
accurately define the target population.
 Types of Research Design

Descriptive Experimental Correlational Diagnostic

Research Design Research Design Research Design Research Design

Explanatory
Research Design
 • Meaning
• Exploratory research is a
methodology approach that
investigates research
questions that have not previously
been studied in depth.
• Exploratory research is
often qualitative and primary in
Exploratory nature. However, a study with a
large sample conducted in an
Research: exploratory manner can
be quantitative as well. It is also
often referred to as interpretive
research or a grounded theory
approach due to its flexible and
open-ended nature.
 • 1. To generate new ideas or
• 2. To increase the
researcher’s familiarity with
the problem or
Exploratory
• 3. To make a precise
Research - formulation of the problem or
purpose, • 4. To gather information for
clarifying concepts or
• 5. To determine whether it is
feasible to attempt the study.
Types and methodologies of Exploratory
research
 Characteristics of Exploratory research
1. They are not structured studies
2. It is usually low cost, interactive and open ended.
3. It will enable a researcher answer questions like what is the
problem? What is the purpose of the study? And what topics
could be studied?
4. To carry out exploratory research, generally there is no prior
research done or the existing ones do not answer the
problem precisely enough.
5. It is a time consuming research and it needs patience and
has risks associated with it.
6. The researcher will have to go through all the information
available for the particular study he is doing.
7. There are no set of rules to carry out the research per se, as
they are flexible, broad and scattered.
8. The research needs to have importance or value. If the
problem is not important in the industry the research carried
out is ineffective.
• Advantages of Exploratory research
 The researcher has a lot of flexibility and can adapt to changes as the research
progresses.
 It is usually low cost.
 It helps lay the foundation of a research, which can lead to further research.
 It enables the researcher understand at an early stage, if the topic is worth investing the
time and resources and if it is worth pursuing.
 It can assist other researchers to find out possible causes for the problem, which can be
further studied in detail to find out, which of them is the most likely cause for the
problem.
• Disadvantages of Exploratory research
 Even though it can point you in the right direction towards what is the answer, it is
usually inconclusive.
 The main disadvantage of exploratory research is that they provide qualitative data.
Interpretation of such information can be judgmental and biased.
 Most of the times, exploratory research involves a smaller sample, hence the results
cannot be accurately interpreted for a generalized population.
 Many a times, if the data is being collected through secondary research, then there is a
chance of that data being old and is not updated.
 • Experimental research is a type of
quantitative research method where
researchers manipulate independent
variables to observe their effect on
dependent variables. This design is often
used to establish cause-and-effect
relationships.
• Key Components of Experimental Research
Experimental 1. Independent Variable (IV): The variable
that the researcher manipulates.
Research 2. Dependent Variable (DV): The variable that
Design is measured to see the effect of the IV.
3. Experimental Group: The group that
receives the treatment or manipulation of
the IV.
4. Control Group: The group that does not
receive the treatment.
5. Random Assignment: Participants are
randomly assigned to either the
experimental or control group to ensure
equal representation.
1. Pre-experimental study design:
This is the simplest form of experimental design. It lacks random assignment
and often doesn't control for all external variables, making it weaker in
establishing cause-and-effect relationships.
• One-Shot Case Study:
Description: A single group is exposed to a treatment or condition, and then
the outcome is measured. No comparison group is used.
Example: A teacher gives a new teaching method to a class and then
measures the students' performance in a test, without comparing to a group
that didn’t receive the method.
• One-Group Pretest-Posttest:
A group is tested before and after the treatment, allowing for a comparison
between the pretest and posttest results.
Example: Students are tested on their math skills, then taught using a new
instructional technique, and then tested again to measure improvement.
1. Pre-experimental study design:
• Static Group:
Description: Two groups are studied—one
exposed to the treatment and one that isn’t.
However, there's no random assignment, which
can lead to selection bias.
Example: In a classroom, one group of students
uses educational software, while another group
uses traditional methods. Their test scores are
then compared.
 2. True Experimental Design
This design is more rigorous, with random assignment and control over
external variables, allowing for stronger cause-and-effect conclusions.
• Pretest-Posttest Control Group:
Participants are randomly assigned to either the control or
experimental group. Both groups are tested before and after the
treatment.
Example: A clinical trial where patients are randomly assigned to
receive either a new drug or a placebo. Their health is assessed both
before and after the treatment.
• Pretest-Only Control Group:
Only the posttest is conducted after the treatment. Random
assignment helps eliminate biases, even without a pretest.
Example: A company implements a new training program for a random
group of employees, and after the program, their productivity is
measured without an initial test.
 2. True Experimental Design
• Solomon Four-Group:
Combines both pretest-posttest and posttest-only designs,
involving four groups. Two receive the treatment, and two
do not. This design helps test the influence of the pretest
on the results.
Example: A researcher wants to test a new teaching
method’s effectiveness on students. Group A and Group B
are tested before and after the method, while Group C and
Group D are only tested after the method. Group A and
Group C receive the method, and Group B and Group D do
not.
 3. Quasi-Experimental Design
This design lacks random assignment but includes control groups or other
methods of comparison. It’s used when randomization is not feasible.
• Randomized Blocks:
Participants are divided into blocks based on a particular characteristic, and then
within each block, participants are randomly assigned to different treatments.
Example: A school divides students based on prior academic performance (high,
medium, low) and then randomly assigns students within each block to either a
new teaching method or a standard method. The performance is then compared.
• Latin Square:
A balanced design where each treatment appears in each position in a sequence.
It's used to control for two confounding variables simultaneously.
Example: Suppose an agricultural experiment is testing three different types of
fertilizers (A, B, and C) on crop yield. There are two confounding variables: soil
type (rows) and field position (columns). The Latin Square design ensures each
fertilizer is applied once in every row (soil type) and column (field position).
 3. Quasi-Experimental Design
For example, in a 3x3 Latin Square design:
Soil Type/Field
1 2 3
Position
Soil 1 A B C
Soil 2 B C A
Soil 3 C A B

• Factorial Design:
This involves studying two or more independent variables
simultaneously to observe their effects individually and
combined.
Example: A company tests the effectiveness of a new
advertising campaign by varying two factors—media type (TV,
social media) and message type (emotional, rational)—to see
which combination works best.
 4. Statistical Experimental Design
This design involves time-based or multiple observations to establish
patterns or trends.
• Time Series:
Multiple observations are made over time before and after the treatment
to assess the treatment’s impact.
Example: A city wants to assess the impact of a new traffic signal system.
Traffic flow is measured over several months before and after the system is
implemented to identify changes.
• Multiple Time Series:
Similar to time series but involves comparing two or more groups over
time, with at least one group receiving the treatment.
Example: The performance of two sales teams is tracked for several
months. One team receives a new sales strategy, and the other continues
with the current strategy. Their performance is compared over time to
determine the effectiveness of the new approach.
 Advantages and Disadvantages of Experimental
Research Design
Advantages:
• Experimental research is one of the few methods that can clearly determine a cause-and-effect
relationship between variables by controlling and manipulating the independent variable.
• Researchers have strict control over external variables, ensuring that the results are due to the
manipulation of the independent variable and not other factors.
• Experiments are often repeatable, allowing other researchers to replicate the study in different contexts
to verify results. This strengthens the reliability of the findings.
• The use of experimental controls allows for precise measurements of variables, leading to accurate data
collection and results.
• Techniques like random assignment and blinding (single or double-blind) reduce bias, ensuring more
objective and reliable results.
Disadvantages:
• Many experiments are conducted in controlled, artificial environments (such as labs), which may not
accurately reflect real-world scenarios. This reduces external validity.
• Certain experiments, especially those involving human subjects, can raise ethical issues. Manipulating
variables such as health, emotions, or behaviors can sometimes be harmful or controversial.
• Human behavior is complex and influenced by numerous variables. It’s difficult to account for all
potential confounding variables, which may limit the accuracy of the results.
• Since experimental research often involves specific conditions and selected participants, the results
may not always generalize to a broader population.
• Experimental research often requires a significant investment of time, money, and resources. The setup,
execution, and analysis of the data can be labor-intensive.
 • Conclusive research is a type of quantitative
research designed to provide definitive and
conclusive answers to specific research
questions. It's often used to gather data that
can be used to make informed decisions.
• Key Characteristics of Conclusive Research
Conclusive • Structured: Uses predefined data collection
instruments and procedures.
Research • Quantitative: Relies on numerical data.
• Objective: Aims to provide unbiased and
Design: objective findings.
• Descriptive: Often used to describe
characteristics, behaviors, or opinions of a
population.
• Causal: Can be used to establish cause-and-
effect relationships.
 Types of Conclusive Research

Causal Research:
Descriptive Research:
Meaning: Focuses on describing Meaning: Identifies cause-and-effect
characteristics of a population or relationships by manipulating variables and
phenomenon. It answers the "what," controlling conditions. It answers the
"where," "when," and "how" questions but "why" question.
does not determine cause-and-effect Example: A marketer wants to know if
relationships. increasing the price of a product will lead
Example: A company conducts a survey to decreased sales. The researcher
to measure customer satisfaction levels conducts an experiment by adjusting prices
across different product lines. The goal is in different regions and measuring the
to describe how satisfied customers are resulting changes in sales.
without determining why they feel that
way.
 Types of Conclusive Research
Descriptive Research Types: Causal Research Types:
Cross-sectional: Collects data from a Before-and-After Study : Compares
sample of the population at a single point measurements taken before and after the
in time. introduction of a change or treatment.
Example: A fast-food chain surveys Example: A company measures employee
customers to determine their preferences productivity before and after implementing
for new menu items by analyzing current a new performance management system
trends. to determine its impact.
Longitudinal: Collects data from the same Field Experiment: Experiments conducted
sample over a period of time to observe in a real-world setting where researchers
changes. manipulate variables and observe
Example: A car manufacturer tracks outcomes.
customer satisfaction with a specific model Example: A retail store tests the
over five years to see how satisfaction effectiveness of different in-store
changes over time. advertising techniques by applying them in
different locations and measuring sales
growth.
 Cross-sectional study Longitudinal study
Cross-sectional studies are quick to
conduct as compared to longitudinal Longitudinal studies may vary from a
studies. few years to even decades.
A longitudinal study requires a
A cross-sectional study is conducted researcher to revisit participants of the
at a given point in time. study at proper intervals.

Cross-sectional study is conducted Longitudinal study is conducted with

with different samples. the same sample over the years.

Cross-sectional studies cannot pin Longitudinal study can justify cause-

down cause-and-effect relationship. and-effect relationship.
Multiple variables can be studied at Only one variable is considered to
a single point in time. conduct the study.
Since the study goes on for years
Cross-sectional study is longitudinal study tends to get
comparatively cheaper. expensive.
 Conclusive Research Design:

Advantages of Conclusive Disadvantages of

Research Conclusive Research
• Provides definitive and • Can be expensive and
conclusive answers. time-consuming.
• Can be used to make • May not be suitable for
informed decisions. exploring new research
• Can be replicated. areas.
• May not capture the
nuances of human
behavior.
 • Correlational research is a type of quantitative
research that investigates the relationship
between two or more variables. It helps to
understand how changes in one variable are
associated with changes in another.
Correlatio • Key Characteristics of Correlational Research

nal Measures the relationship: It doesn't establish
cause-and-effect relationships but rather
Research measures the strength and direction of the
relationship between variables.
Design  No manipulation: Correlational research does not
involve manipulating variables; it simply observes
and measures them.
 Quantitative data: It relies on numerical data to
analyze the relationship between variables.
 • Diagnostic research is a type of quantitative
research that aims to identify the underlying
causes of a problem or issue. It involves
investigating the root causes of a problem to
develop effective solutions.
Diagnostic • Key Characteristics of Diagnostic Research
• Problem-focused: It focuses on identifying
Research the specific causes of a problem.
• In-depth analysis: It requires a thorough
Design investigation of various factors that may
contribute to the problem.
• Data-driven: It relies on data to identify the
root causes of the problem.
• Action-oriented: The goal is to use the
findings to develop effective solutions.
 • ABC Retail is an online retail
company that has seen rapid
growth in the past five years.
However, management has
noticed a decline in customer
case satisfaction ratings,
study particularly regarding
customer service and delivery
times. The company wants to
explore the root causes
behind these negative ratings
and gather insights to
improve its operations.
• Research Problem:
Why are customer
satisfaction levels declining
at ABC Retail, specifically in
the areas of customer
service and delivery times?
 • Literature Search: To review best
practices in customer service and
logistics management for online retail.
• Experience Survey: Conducting
Exploratory interviews with customer service agents
Research and logistics personnel to gather their
insights.
Methods • Focus Groups: Organizing sessions with
customers to understand their
Used: perspectives on service and delivery.
• Case Method: In-depth examination of
specific cases of customer complaints
regarding service and delivery delays.
• What was the primary objective of the
exploratory research conducted by ABC Retail?
 • The primary objective was to
What was explore the reasons behind
the primary the declining customer
objective of satisfaction levels, particularly
the focusing on the company's
exploratory customer service and delivery
research systems. The research aimed
conducted to uncover underlying issues,
by ABC gain insights, and provide a
Retail? basis for future, more
detailed studies or solutions.
• How was the literature search used to inform
the research?
 • The literature search involved
reviewing academic studies,
industry reports, and articles on
How was effective customer service
the strategies and logistics
literature management in e-commerce.
The findings revealed best
search practices, such as the importance
used to of efficient communication
inform the between service agents and
customers, and how leading
research? companies manage delivery
times to enhance customer
satisfaction.
• What insights were gathered from the
experience survey conducted with
employees?
 • Through interviews with
customer service agents, it was
What insights found that high call volumes and
were a lack of sufficient training were
gathered causing delays in resolving
from the customer queries. Logistics
personnel mentioned
experience inefficiencies in the warehouse
survey management system, which
conducted were contributing to delivery
with delays. Both groups felt that
employees? improving communication
between departments could
resolve many of these issues.