Chapter Three

Research Design Formulation

3-1
 Focus of This Relationship to Relationship to
Marketing
Chapter Previous Chapter Research Process
• Definition and • Marketing
Problem Definition
Classification of Research Process
Research Design (Chapter 1)
• Exploratory • Specification of Approach to Problem
Research Design the Information
• Descriptive Needed Research Design
Research Design (Chapter 2)
• Causal Research Field Work
Design
Data Preparation and
Analysis

Report Preparation
and Presentation

Copyright © 2012 Pearson Education, Inc. Chapter 3 - 2

Define the Marketing Research Problem

Develop an Approach to the Problem

Formulate the Research Design

Copyright © 2012 Pearson Education, Inc. Chapter 3 - 3

 A research design is a framework or blueprint
for conducting the marketing research project.
It details the procedures necessary for obtaining
the information needed to structure or solve
marketing research problems.

Copyright © 2012 Pearson Education, Inc. Chapter 3 - 4

 Define the information needed
 Design the exploratory, descriptive, and/or
causal phases of the research
 Specify the measurement and scaling
procedures
 Construct and pretest a questionnaire
(interviewing form) or an appropriate form for
data collection
 Specify the sampling process and sample size
 Develop a plan of data analysis

Copyright © 2012 Pearson Education, Inc. Chapter 3 - 5

 Research Design

Exploratory Research Design Conclusive Research Design

Descriptive Research Causal Research

Cross-Sectional Design Longitudinal Design

Copyright © 2012 Pearson Education, Inc. Chapter 3 - 6

 Exploratory Conclusive
Objective: To provide insights and To test specific hypotheses
understanding. and examine relationships.

Characteristics: Information needed is defined only Information needed is clearly

loosely. defined.

Research process is flexible and Research process is formal

unstructured. and structured.

Sample is small and non Sample is large and

representative. representative.

Data analysis is qualitative. Data analysis is quantitative.

Findings: Tentative. Conclusive.

Outcome: Generally followed by further Findings used as input into

exploratory or conclusive research. decision making.

Copyright © 2012 Pearson Education, Inc. Chapter 3 - 7

 Exploratory Descriptive Causal
Discovery of ideas Describe market Determine cause and
Objective: and insights. characteristics or functions. effect relationships.
Flexible. Marked by the prior Manipulation of one or
formulation of specific more independent
Character- Versatile. hypotheses. variables.
istics: Often the front end Preplanned and structured Control of other
of total research design. mediating variables.
design.
Expert surveys. Secondary data Experiments.
(quantitative).
Pilot surveys.
Case studies. Panels.
Method:
Secondary data Observational
(qualitative). and other data.
Qualitative
Research.
Copyright © 2012 Pearson Education, Inc. Chapter 3 - 8
 Formulate a problem or define a problem more
precisely
 Identify alternative courses of action
 Develop hypotheses
 Isolate key variables and relationships for
further examination
 Gain insights for developing an approach to the
problem
 Establish priorities for further research

Copyright © 2012 Pearson Education, Inc. Chapter 3 - 9

 Survey of experts
 Pilot surveys
 Case studies
 Secondary data analyzed in a qualitative way
 Qualitative research

Copyright © 2012 Pearson Education, Inc. Chapter 3 - 10

 Qualitative research
› Pilot surveys tend to be less structured than the
large scale surveys in that they generally contain
more open ended questions and sample size is
much smaller.
› Case studies involve an intensive examination
of a few selected cases of phenomenon of
interest. The cases could be consumers, stores,
firms or other units such as markets, websites
etc.

Copyright © 2012 Pearson Education, Inc. Chapter 2 - 11

 To describe the characteristics of relevant groups, such
as consumers, salespeople, organizations, or market
areas. E.g. Heavy users of What’s app
 To estimate the percentage of units in a specified
population exhibiting a certain behavior. E.g. Percentage
of heavy users of What’s app also using Skype
 To determine the perceptions of product characteristics.
E.g. How do customers perceive departmental stores in
terms of friendliness of their staff?
 To determine the degree to which marketing variables are
associated. E.g. To what extent is shopping at
department stores related to eating out?
 To make specific predictions. E.g. What will be the sales
of a supermarket in food items in a
Copyright specific
© 2012 region?
Pearson Education, Inc. Chapter 3 - 12
 Secondary data analyzed in a quantitative as
opposed to a qualitative manner
 Surveys
 Panels
 Observational and other data

Copyright © 2012 Pearson Education, Inc. Chapter 3 - 13

 Descriptive Studies

Consumer Market
Sales Studies Perception and Characteristic
Behavior Studies
Studies

•Market Potential •Image •Distribution

•Market Share •Product Usage •Competitive
•Sales Analysis •Advertising Analysis
•Pricing

Copyright © 2012 Pearson Education, Inc. Chapter 3 - 14

 A cross-sectional design involves the
collection of information from any given sample
of population elements only once.
› In single cross-sectional design, only one
sample of respondents is drawn from target
population and information from it is obtained
only once. Also called sample survey research
design.
› In multiple cross-sectional design, two or
more samples are drawn and information from
each sample is obtained only once.

Copyright © 2012 Pearson Education, Inc. Chapter 3 - 15

 In a longitudinal design, a fixed sample (or
samples) of population elements is measured
repeatedly on the same variables.
 A longitudinal design differs from a cross-
sectional design in that the sample or samples
remain the same over time.
 A panel consists of a sample of respondents
generally households that have agreed to
provide information at specified intervals over
an extended period.

Copyright © 2012 Pearson Education, Inc. Chapter 3 - 16

Cross- Sample
Sectional Surveyed
Design at T1

Same
Sample Sample
Longitudinal
Surveyed also
Design
at T1 Surveyed
at T2

Time T1 T2

Copyright © 2012 Pearson Education, Inc. Chapter 3 - 17

 Cross-Sectional Longitudinal
Evaluation Criteria
Design Design

Detecting change - +

Large amount of data collection - +

Accuracy - +

Representative sampling + -

Response bias + -

Note: A + indicates a relative advantage over the other design whereas

a - indicates a relative disadvantage.

Copyright © 2012 Pearson Education, Inc. Chapter 3 - 18

 It used to understand the cause and effect
relationships and is appropriate for the following
uses
› To understand which variables are the cause
(independent variables) and which variables are
the effect (dependent variables) of a
phenomenon
› To determine the nature of the relationship
between the causal variables and the effect to be
predicted
 METHOD: Experiments
Copyright © 2012 Pearson Education, Inc. Chapter 3 - 19
 Exploratory
Research Conclusive
Research
(a) - Secondary
- Descriptive/
Data Analysis
Causal
- Focus Group

Conclusive
Research
(b) - Descriptive/
Causal

Exploratory
Conclusive Research
Research
(c) - Descriptive/
- Secondary
Data Analysis
Causal
- Focus Group

Copyright © 2012 Pearson Education, Inc. Chapter 3 - 20

 Define the Information Needed

Design the Exploratory, Descriptive, and/or Causal Phases of the Research

Specify the Measurement and Scaling Procedures

Construct a Questionnaire

Specify the Sampling Process and the Sample Size

Develop a Plan of Data Analysis

Copyright © 2012 Pearson Education, Inc. Chapter 3 - 21

Copyright © 2012 Pearson Education, Inc. Chapter 3 - 22
 Total Error

Random Sampling Error Non sampling Error

Response Error Non response Error

Researcher Interviewer Respondent

Errors Errors Errors

Copyright © 2012 Pearson Education, Inc. Chapter 3 - 23

 Total Error is the variation between the true mean
value in the population of the variable of interest and the
observed mean value obtained in the marketing
research project.
 Random Sampling Error occurs because the sample
selected is an imperfect representation of the population
of interest. (Variation between the true mean value for
the population and true mean value for the original
sample)
 Non sampling error occurs because of sources other
than sampling, random or nonrandom. Could be
because of errors in problem definition, approach,
scales, questionnaire design, interviewing, data
preparation and analysis. Copyright © 2012 Pearson Education, Inc. Chapter 3 - 24
 Response Errors occur when respondents
give incorrect answers or their answers are
misrecorded or misanalysed. Types of response
errors are
› Researcher Errors
› Interviewer Errors
› Respondent Errors
 Non response Errors arise when some of the
respondents included in the study do not
respond (refusals or not at home).

Copyright © 2012 Pearson Education, Inc. Chapter 3 - 25

 Surrogate information error defined as variation
between the information needed for MRP and info
sought by researcher. E.g. When price of brand is
taken to measure quality, assuming that higher
price means high quality, which may not be true.
 Measurement error defined as variation between
the info sought and information generated by the
measurement process employed by the researcher.
E.g. Store needs customer feedback at the counter
purchases, whereas customer feedback is taken
from those who bought online.

Copyright © 2012 Pearson Education, Inc. Chapter 3 - 26

 Population definition error defined as variation
between the actual population relevant to the
problem at hand and population as defined by the
researcher. E.g. population of affluent households
may be defined as
› Households with income > Rs. 200,000/month
› Top 5% of the households
› Households with spendable income 30% higher than
other households
In this case the number and characteristics of households
varies depending upon the case taken.

Copyright © 2012 Pearson Education, Inc. Chapter 3 - 27

 Sampling frame error defined as variation
between the population defined by the researcher
and the population as implied by the sampling
frame. E.g. Telephone directory does not accurately
represent the population of potential customers
because of unlisted, disconnected and new
numbers.
 Data analysis error encompasses errors that
occur when raw data from questionnaires are
transformed into research findings. E.g.
inappropriate statistical procedure used for data
analysis.
Copyright © 2012 Pearson Education, Inc. Chapter 3 - 28
 Respondent selection error occurs when
interviewers select respondents other than
those specified by the sampling design or in a
manner inconsistent with the sampling design.
E.g. In a readership survey, a nonreader is
selected for interview but is classified as a
reader for a magazine.
 Questioning error shows errors made in
asking questions of the respondents or not
probing when more information is needed. E.g.
Interviewer does not use the exact wording of
the questionnaire.
Copyright © 2012 Pearson Education, Inc. Chapter 3 - 29
 Recording error arises due to errors in
hearing, interpreting and recording the answers
given by the respondents. E.g. Interviewer gives
a positive response but interviewer records it as
a negative/neutral one.
 Cheating error arises when the interviewer
fabricates answers to the part or all of the
interview. E.g. interviewer fills in the
questionnaire himself/herself.

Copyright © 2012 Pearson Education, Inc. Chapter 3 - 30

 Inability error results from the respondent’s
inability to provide accurate answers. E.g.
Respondent may not provide accurate answers
due to boredom, fatigue, faulty recall, question
format etc.
 Unwillingness error arises from respondent’s
unwillingness to provide accurate information.
E.g. Respondents may intentionally misreport
their answers because of a desire to provide
socially acceptable answers, avoid
embarrassment or to please the interviewer.
Copyright © 2012 Pearson Education, Inc. Chapter 3 - 31
 Help us to ensure that the marketing research project is
completed within the give resources i.e. financial, time,
personnel and other.
 Critical path method (CPM) involves dicing the
research project into component activities, determining
their sequence and estimating time required for each.
 Program evaluation and review technique (PERT) is
probability based scheduling approach that recognizes
and measures the uncertainty of project measurement.
 Graphical evaluation and review technique (GERT)
in which both completion probabilities and activities are
built into a graph.

Copyright © 2012 Pearson Education, Inc. Chapter 3 - 32

Copyright © 2012 Pearson Education, Inc. Chapter 3 - 33
 Executive summary
 Background
 Problem definition/Objectives of the research
 Approach to the problem
 Research design
 Field work/Data collection
 Data analysis
 Reporting
 Cost and Time
 Appendices
Copyright © 2012 Pearson Education, Inc. Chapter 3 - 34
The components of a research design may be
summarized by the acronym DESIGN:
D ata analysis plan
E xploratory, descriptive, causal design
S caling and measurement
I nterviewing forms: questionnaire design
G enerating the needed information
N umber: Sample size and plan

Copyright © 2012 Pearson Education, Inc. Chapter 11 - 35