RESEARCH DESIGN

UNIT-2

-Kamalpreet Kaur Paposa

Contents

• Exploratory Research Designs: Secondary data analysis;

Qualitative research, Classification of qualitative research
procedures, focus groups, interviews and projective
techniques; Qualitative Vs Quantitative Research.

• Descriptive Research Designs: Survey Methods; Observation

Methods, Behavioral Vs Non-behavioral observation. Survey
Vs Observation.

• Causal Research Designs: Conditions of causality, role of

validity in experimentation, classification of experimental
designs.
Introduction

• Decisions regarding what, where, when, how much

• The research design is the master plan

specifying the methods and procedures for
collecting and analyzing the needed
information.
Introduction

• A research design is the "blue print" of the study.

• The design of a study defines the study type and sub
types, research question, hypotheses, independent
and dependent variables, experimental design, and, if
applicable, data collection methods and a statistical
analysis plan. Research design is the framework that
has been created to seek answers to research
questions.
• A detailed outline of how an investigation will take
place.
• A research design will typically include how data is
to be collected, what instruments will be employed ,
how the instruments will be used and the
intended means for analyzing data collected.
The designing decisions happen to be in respect of:
– (i) What is the study about?
– (ii) Why is the study being made?
– (iii) Where will the study be carried out?
– (iv) What type of data is required?
– (v) Where can the required data be found?
– (vi) What periods of time will the study include?
– (vii) What will be the sample design?
– (viii) What techniques of data collection will be used?
– (ix) How will the data be analyzed?
– (x) In what style will the report be prepared?
• The important features of a research design
– (i) a plan
• specifies the sources & types of information
relevant to the research problem
– (ii) a strategy
• which approach will be used for gathering and
analyzing the data.
– (iii) the time and cost budgets
• most studies are done under these two
constraints

8/42
• Research design must, at least, contain—
–(a) a clear statement of the research
problem;
–(b) procedures and techniques to be
used for gathering information;
–(c) the population to be studied;
–(d) methods to be used in processing
and analyzing data
9/42
A Classification of Marketing Research Designs

Research Design

Exploratory Conclusive
Research Design Research Design

Descriptive Causal
Research Research

Cross-Sectional Longitudinal
Design Design

Single Cross- Multiple Cross-

Sectional Design Sectional Design
Types of Research Design
Exploratory Research Design

• Exploratory
– “discovery”

• Descriptive
– “relationships/ characteristics

• Causal
– “cause-and-effect”
 Overview of Research Design
Uses Types

•Formulate problems more precisely •Literature search

•Develop Hypotheses •Experience survey
Exploratory •Establish priorities for research •Analysis of select cases
Research •Eliminate impractical ideas •Interviews
•Clarify concepts •Ethnographies
•Focus groups
•Etc.
•Describe segment characteristics
Descriptive •Estimate proportion of people
Research who behave in a certain way
•Longitudinal study
•Make specific predictions
•Panels
•Sample Survey
Causal •Provide evidence regarding causal
Research relationships
•Rule out all other explanations •Laboratory experiment
•Field experiment
• The choice of the most appropriate design
depends largely on the objectives of the
research and how much is known about the
problem and these objectives

• The overall research design for a project may

include one or more of these three designs as
part(s) of it

• Further, if more than one design is to be used,

typically we progress from Exploratory toward
Causal.
Types of Research Design
ExploratoryResearch

• Exploratory research is used in cases where the

marketer has little or no understanding about the
research problem due to lack of proper information.
• For example, a marketer has heard about social media
marketing techniques which are employed by their
competitors with great success but he is not familiar
with using these for his products/services.
• He needs to use exploratory market research to
gain/discover insights about this situation. Thus when the
goal of the marketer is to precisely formulate problems,
clear concepts, gain insights, eliminate impractical ideas
and form hypotheses then exploratory research is used.
• Exploratory research follows and unstructured format and
makes use of qualitative techniques, secondary research
and experts opinions. For example, the marketer from the
previous case can use books, case studies, focus groups,
expert interviews and survey techniques to conduct
exploratory research.
• The results of exploratory research can’t be used for marketing
decisions in most cases at least not directly. Then the question
arises why to do exploratory research in the first place? Well
the answer is the core goal of exploratory research is to equip
marketers with enough information to facilitate marketers plan
a format research design correctly. For example by conducting
exploratory research the marketer can find out that the
competition is using popular social media channels like
Facebook, Twitter, LinkedIn and YouTube to reach target
consumers effectively and successfully engaging customers
with the brand directly. Now with this information he can plan
a formal research design to test his hypothesis.
Purpose of Exploratory Research
• Formulate a problem or define problem more
precisely
• Identify alternative course of action
• Develop hypothesisis
• Isolate key variables and relationship for further
examination
• Gain insights for developing an approach to the
problem
• Establish priorities for further research
Characteristics of Exploratory Research
• The exploratory research design must possess the
following characteristics.
• Business Importance: Unless the issue has a place in the industry or has
business value, its study will be ineffective and worthless.
• Practical Element: If needs to have practical value to the management. If it
does not have any practical value it will be unproductive for business
decisions.
• Combinations of Theory: Mere practical importance of the challenge has no
meaning unless it is in accordance with theory. If a specific problem is in
accordance with certain theoretical aspects it shall be easy for the
researcher to assess its utility or move forward with his study in the right
direction.
• Dependable and Useful Facts: In the absence of trustworthy and valuable
facts, the study of the problem will have no managerial significance.
• - See more at: http://universalteacher.com/1/features-of-exploratory-
research/#sthash.wj9bfptg.dpuf
Advantages
Limitations

• Findings determined by qualitative research could be

susceptible to significant interpreter bias.
• The majority of exploratory methods make use of
modest samples, that might not be representative
since they have not been chosen on a probability basis
• A good idea may be declined or a bad idea may be
adopted
Limitations

• Findings determined by qualitative research could be

susceptible to significant interpreter bias. Conclusions
from focus group interviews could be unclear. How
should a face expression or nod of the head be
interpreted? Have subjects completely understood the
idea or concept behind a nonexistent item? Have
participants overstated their curiosity since they have a
tendency to like all new items? Due to these kinds of
issues in interpretation, exploratory findings should be
regarded as preliminary. - See more at:
http://universalteacher.com/1/disadvantages-of-
exploratory-research/#sthash.2mgVSMjf.dpuf
Limitations…

• One other issue with exploratory methods relates to

the capability to make forecasts from the results. The
majority of exploratory methods make use of modest
samples, that might not be representative since they
have not been chosen on a probability basis. Case
studies, for instance, could have been selected simply
because they represent extremely good or very bad
examples of a scenario as opposed to the average
situation. - See more at:
http://universalteacher.com/1/disadvantages-of-
exploratory-research/#sthash.2mgVSMjf.dpuf
Limitations….

• The biggest drawback of exploratory research is that a good

idea with promise could be declined due to conclusions at the
exploratory stage. On the contrary, when everything appears
good in the exploratory stage, the temptation is to market the
product without additional research. Instead, after completing
exploratory work, management must decide whether the
advantages of the additional information would be worth the
cost of further study. Generally when a major commitment of
resources is at risk, performing the quantitative study is
definitely worth the effort. Sometimes good marketing
research only documents the obvious. However, the objective
of company is to generate a profit, and decision makers want
to be certain that they have made the right choice. - See more
at: http://universalteacher.com/1/disadvantages-of-exploratory-
research/#sthash.2mgVSMjf.dpuf
Causal Research/Experimental Rsearch

• Purpose
– Does a change in X cause a change in Y?
• Experiments
– Laboratory experiments
– Field experiments
• Let’s take some test cases where causal research can
be used:
• What will happen to sale of my product if I change
the packaging of the product?
• What will happen to sale of my product if I change
the design of the product?
• What will happen to sale of my product if I change
the advertising?
Example of Causal Research

• cereal brand owner wants to learn if they will receive

more sales with their new cereal box design. Instead
of conducting descriptive research by asking people
whether they would be more likely to buy their cereal
in its new box, they would set up an experiment in
two separate stores. One will sell the cereal in only its
original box and the other with the new box. Taking
care to avoid any outside sources of bias, they would
then measure the difference between sales based on
the cereal packaging. Did the new packaging have
any effect on the cereal sales? What was that effect?
 Objective

• To obtain evidence of cause-and-effect relationships

• To understand which variables are the cause and

which variables are the effect of a phenomena

• To determine the nature of the relationship between

the causal variables and the effect to be predicted
Concept of Causality
• Experimentation is commonly used to infer causal
relationship
A statement such as "X causes Y " will have the
following meaning to an ordinary person and to a
scientist.
____________________________________________________
Ordinary Meaning Scientific Meaning
____________________________________________________
X is the only cause of Y. X is only one of a number of
possible causes of Y.

X must always lead to Y The occurrence of X makes the

(X is a deterministic occurrence of Y more probable
cause of Y). (X is a probabilistic cause of Y).

It is possible to prove We can never prove that X is a

that X is a cause of Y. cause of Y. At best, we can
infer that X is a cause of Y.
Principle of Causality

• Causality is a genetic connection of phenomena through which one

thing (the cause) under certain conditions gives rise to, causes
something else (the effect). The essence of causality is the
generation and determination of one phenomenon by another.

• In this respect causality differs from various other kinds of

connection, for example, the simple temporal sequence of
phenomena, of the regularities of accompanying processes. For
example, a pinprick causes pain or brain damage causes mental
illness.

• Causation means that a change in one variable will produce a

change in another. Association measures, by themselves do not
demonstrate causation. Correlation does not imply causation, both
variables may be responding to changes in an unobserved or
unmeasured variable.
Conditions for Causality

• Concomitant variation is the extent to which a

cause, X, and an effect, Y, occur together or vary
together in the way predicted by the hypothesis under
consideration.
• The time order of occurrence condition states that
the causing event must occur either before or
simultaneously with the effect; it cannot occur
afterwards.
• The absence of other possible causal factors means
that the factor or variable being investigated should
be the only possible causal explanation.
Definitions and Concepts
• Independent variables are variables or alternatives that are
manipulated and whose effects are measured and compared,
e.g., price levels.
• Test units are individuals, organizations, or other entities whose
response to the independent variables or treatments is being
examined, e.g., consumers or stores.
• Dependent variables are the variables which measure the
effect of the independent variables on the test units, e.g., sales,
profits, and market shares.
• Extraneous variables are all variables other than the
independent variables that affect the response of the test units,
e.g., store size, store location, and competitive effort.
Experimental Design
Experimental Design

• Experimental designs are structured plans for

conducting experiments and collecting data to address
research questions or test hypotheses.

• They help researchers control and manipulate

variables to make valid inferences about the
relationships between variables.
Experimental Design

An experimental design is a set of procedures specifying:

◼ the test units and how these units are to be divided into
homogeneous subsamples,
◼ what independent variables or treatments are to be
manipulated,
◼ what dependent variables are to be measured; and
◼ how the extraneous variables are to be controlled.
 A Classification of Experimental Designs
Figure 7.1

Experimental Designs

Pre-experimental True Experimental Quasi

Statistical
Experimental

One-Shot Case Pretest-Posttest Time Series Randomized

Study Control Group Blocks

One Group Pretest- Posttest: Only Control Multiple Time Latin Square
Posttest Group Series

Static Group Solomon Four-Group Factorial Design

A Classification of Experimental Designs

A. Pre-experimental designs are research designs that lack the

random assignment of participants to different conditions or the
use of a control group. These designs are generally considered
weaker in terms of establishing causation compared to true
experimental designs. Pre-experimental designs are often used
when random assignment is not feasible or ethical.
B. In true experimental designs, True experiments involve the
manipulation of an independent variable and random assignment
of participants to different experimental conditions. These
designs are considered more rigorous in establishing cause-and-
effect relationships
A Classification of Experimental Designs

• C. Quasi-experimental designs Quasi-experimental designs

lack true random assignment of participants to experimental
conditions, making it more challenging to establish causation.
However, they are often more practical and ethical in certain
research settings. Taking series of observation before and after
the treatment.

• D. A statistical design is a series of basic experiments that

allows for statistical control and analysis of external variables:
randomized block design, Latin square design, and factorial
designs.
• To make things easier, the following will act as
representations within particular designs:
• X--Treatment
• O--Observation or measurement
• R--Random assignment
A. Pre-experimental designs
i. One-Shot Case Study

X 01
• A single group of test units is exposed to a treatment X.
• A single measurement on the dependent variable is taken
(01).
• There is no random assignment of test units.
• The one-shot case study is more appropriate for
exploratory than for conclusive research.
A. Pre-experimental designs
i. One-Shot Case Study………
• An example of one such design might be a one survey
of unemployed people in a specific local area to
assess their health status and the impact of
unemployment on health. Thus there is no attempt to
approximate to the classical experiment. There is no
comparison group of employed people, there is no
attempt to study changes over time and the sample
selected
A. Pre-experimental designs
ii. One-Group Pretest-Posttest Design

01 X 02
• A group of test units is measured twice.
• There is no control group.
• The treatment effect is computed as 02 – 01.
• The validity of this conclusion is questionable since extraneous
variables are largely uncontrolled.
• A single case is observed at two time points, one before the treatment
and one after the treatment. Changes in the outcome of interest are
presumed to be the result of the intervention or treatment. No control
or comparison group is employed.
Research Question: Does a mindfulness
meditation program lead to a reduction in
symptoms of anxiety?
• Design:
1. Participants: Select a group of individuals experiencing symptoms
of anxiety.
2. Pretest: Administer a pretest to measure the level of anxiety
symptoms in the participants.
3. Intervention: Implement a mindfulness meditation program for the
participants.
4. Posttest: Administer a posttest to measure anxiety symptoms after
the completion of the mindfulness program.
5. Data Analysis: Use statistical tests to compare pretest and posttest
scores.
6. Interpretation: Determine whether there is a statistically significant
reduction in anxiety symptoms after participating in the
mindfulness meditation program.
A. Pre-experimental designs
iii. Static Group Design
EG: X 01
CG: 02

• A two-group experimental design.

• The experimental group (EG) is exposed to the treatment, and
the control group (CG) is not.
• Measurements on both groups are made only after the
treatment.
• Test units are not assigned at random.
• The treatment effect would be measured as 01 - 02.
 Research Question: Does participating in a
time management workshop lead to a
significant improvement in productivity
compared to a group that does not receive
the workshop?
• Design:
1. Treatment Group (Group A):
1. Participants in Group A are selected to attend a time management workshop.
2. Control Group (Group B):
1. Participants in Group B do not receive the time management workshop. This group serves as a
comparison to assess the impact of the workshop.
3. Measurement:
1. Measure productivity levels in both Group A and Group B after the workshop.
4. Data Analysis:
1. Compare the productivity levels between Group A (the treatment group) and Group B (the
control group).
5. Interpretation:
Determine whether there is a statistically significant difference in productivity levels between the
two groups. If Group A shows a significantly greater improvement in productivity than Group B, it
may be attributed to the time management workshop.
B. True Experimental Designs:
i. Pretest-Posttest Control Group Design
EG: R 01 X 02
CG: R 03 04

• Test units are randomly assigned to either the experimental or the control
group.

• A pretreatment measure is taken on each group.

• The treatment effect (TE) is measured as:(02 - 01) - (04 - 03).

• Selection bias is eliminated by randomization.

• The other extraneous effects are controlled

Research Question: Does a new teaching method
lead to a significant improvement in students' math
performance compared to the traditional teaching
method?
• Design:
1. Experimental Group (Group A):
1. Participants in Group A receive the new teaching method for math.
2. Control Group (Group B):
1. Participants in Group B receive the traditional teaching method for math.
3. Pretest Measurement:
1. Measure the math performance of both Group A and Group B before the
implementation of the new teaching method.
4. Intervention:
1. Implement the new teaching method for Group A while Group B continues
with the traditional teaching method.
5. Posttest Measurement:
1. Measure the math performance of both Group A and Group B after the
intervention.
6. Data Analysis:
Compare the change in math performance from pretest to posttest in both Group
A and Group B.
B. True Experimental Designs:
ii. Posttest-Only Control Group Design

EG : R X 01
CG : R 02

• The treatment effect is obtained by:

TE = 01 - 02
• Except for pre-measurement, the implementation of this
design is very similar to that of the pretest-posttest control
group design.
Research Question: Does a new teaching method
lead to a significant improvement in students' math
performance compared to the traditional teaching
method?
• Design:
1. Experimental Group (Group A):
1. Participants in Group A receive the new teaching method for math.
2. Control Group (Group B):
1. Participants in Group B receive the traditional teaching method for
math.
3. Intervention:
1. Implement the new teaching method for Group A while Group B
continues with the traditional teaching method.
4. Posttest Measurement:
1. Measure the math performance of both Group A and Group B after
the intervention.
5. Data Analysis:
Compare the math performance scores between Group A and Group B
C. Quasi-Experimental Designs:
i. Time Series Design

01 02 03 04 05 X 06 07 08 09 010

• There is no randomization of test units to treatments.

• Taking series of observation before and after the treatment

• The timing of treatment presentation, as well as which test units

are exposed to the treatment, may not be within the researcher's
control.
C. Quasi-Experimental Designs:
ii. Multiple Time Series Design
EG : 01 02 03 04 05 X 06 07 08 09 010

CG : 01 02 03 04 05 06 07 08 09 010

• If the control group is carefully selected, this design can be an

improvement over the simple time series experiment.

• Can test the treatment effect twice: against the pretreatment

measurements in the experimental group and against the
control group.
D. Statistical Designs

Statistical designs consist of a series of basic experiments that

allow for statistical control and analysis of external variables and
offer the following advantages:

– The effects of more than one independent variable can be

measured.
– Specific extraneous variables can be statistically controlled.
– Economical designs can be formulated when each test unit is
measured more than once.

The most common statistical designs are the randomized block

design, the Latin square design, and the factorial design.
D. Statistical Designs
i. Randomized Block Design

• Is useful when there is only one major external variable, such

as store size, that might influence the dependent variable.

• The test units are blocked, or grouped, on the basis of the

external variable.

• By blocking, the researcher ensures that the various

experimental and control groups are matched closely on the
external variable.
Steps Involved:

Identify the Blocking Variable:

• Determine a factor that is expected to introduce variability or influence the

response variable. This factor becomes the basis for blocking.

Create Homogeneous Blocks:

• Group experimental units into blocks based on the identified factor. Aim for
homogeneity within each block with respect to the blocking variable.

Random Assignment within Blocks:

• Randomly assign experimental units to different treatment conditions

within each block. This ensures that each treatment is represented in each
block.
Apply Treatments and Collect Data:

• Implement the experimental treatments and collect data

on the response variable. This is done for each
combination of treatment and block.
Statistical Analysis:

• Analyze the data using appropriate statistical techniques,

considering the blocking variable. Commonly used
analysis methods include Analysis of Variance (ANOVA)
with blocks.
Example:Does a new fertilizer lead to
a significant increase in crop yield, and
is the effect consistent across different
soil types?
• Randomized Block Design:
• Blocking Variable: Soil Type (sandy, loamy, clay)
• Blocks: Divide the experimental plots into blocks based
on the soil types.
• Random Assignment: Within each block (each soil type),
randomly assign different plots to receive either the new
fertilizer or the standard fertilizer.
• Replication: Apply the treatments to multiple plots
within each block to account for variability within the soil
types.
• Data Collection: Measure crop yield for each plot.
• Analysis:

• Conduct an Analysis of Variance (ANOVA)

considering both the treatment effect and the blocking
effect (soil type). This helps determine if there is a
significant difference in crop yield due to the
fertilizer treatment, while controlling for the potential
impact of different soil types.
D. Statistical Designs
ii. Latin Square Design
• A Latin Square Design is an experimental design used
to control for variability caused by two extraneous
sources simultaneously. This design is particularly
useful when there are two potential confounding
variables, and the researcher wants to ensure that each
level of one variable is paired with each level of the
other variable across different treatment conditions.
D. Statistical Designs
ii. Latin Square Design

• Allows the researcher to statistically control two noninteracting external

variables as well as to manipulate the independent variable.

• Each external or blocking variable is divided into an equal number of

blocks, or levels.

• A Latin square is conceptualized as shown in the table, with the rows and
columns representing the blocks in the two external variables.

• The levels of the independent variable are assigned to the cells in the
table.
Example: Latin Square Design for
Teaching Method Study
1. Independent Variable (IV):
1.Teaching Method (New vs. Traditional)
2. Dependent Variable (DV):
1.Student Performance (measured by test scores)
3. Potential Confounding Variables:
1.Socioeconomic Status (SES)
2.Class Sections
Latin Square Design:

1. Socioeconomic Status (SES):

1. Identify three levels of SES: Low, Medium, High.
2. Class Sections:
1. Identify three class sections: A, B, C.
3. Create a Grid:
1. Create a Latin Square grid where each level of the
independent variable (Teaching Method) appears
once in each row and column, paired with each level
of SES and class section.
D. Statistical Designs
iii. Factorial Design

• Is used to measure the effects of two or more

independent variables at various levels.
• A factorial design may also be conceptualized as a
table.
• In a two-factor design, each level of one variable
represents a row and each level of another variable
represents a column.
Limitations of Experimentation
• Experiments can be time consuming, particularly if the
researcher is interested in measuring the long-term effects.
• Experiments are often expensive. The requirements of
experimental group, control group, and multiple
measurements significantly add to the cost of research.
• Experiments can be difficult to administer. It may be
impossible to control for the effects of the extraneous
variables, particularly in a field environment.
• Competitors may deliberately contaminate the results of a
field experiment.
Research Question:
How do advertising format and message
appeal interact to influence consumer
attitudes toward a product?
• Independent Variables (IVs):
1. Advertising Format:
1. Level 1: Visual
2. Level 2: Auditory
2. Message Appeal:
1. Level 1: Emotional
2. Level 2: Rational
• Dependent Variable (DV):
• Consumer Attitudes toward the Product (measured by a Likert scale)
• Experimental Conditions:
• The factorial design results in four experimental conditions, representing all
possible combinations of the two independent variables:
1. Visual + Emotional Message
2. Visual + Rational Message
3. Auditory + Emotional Message
4. Auditory + Rational Message