Marketing Research
Marketing Research
1
MARKETING RESEARCH
through information –
2
MARKETING RESEARCH
3
Why Market Research?
It is usually said that if marketing would be a train, then market research would be the locomotive. In other
words, market research should ideally be the starting point of any marketing exercise.
Conducting any marketing exercise - be it related to pricing, promotion or distribution of a product or service,
without researching the potential market is as sensible as setting out to sell sand in the Sahara Desert.
Market research provides the answers to all the questions that generally occupy the minds of marketers, at
every stage of the marketing process.
Will there be a demand for my product or service ?
What should be the ideal price of my offering - one that ensures that I earn the maximum profit ?
Should I place my product only in urban markets or distribute even in the rural areas ?
Is the fourfold growth in my sales figures a consequence of our latest television commercial ?
How satisfied are our customers with the after sales services we provide ?
It's really crucial to understand your target market before undertaking any marketing exercise, unless you
don't mind risking your hard-earned money and precious time on activities that might not get you the results
you want.
Simply put, ignoring market research before marketing is synonymous with firing a shot in a pitch dark room,
and still hoping that the bullet hits the bulls eye.
_________________________________________________________________________________
Source: IMRB [http://www.imrbint.com/market/index.html]
4
Independent Variables Dependent Variables
(Causes) (Effects)
Information Inputs
6
MARKETING MANAGEMENT PROCESS
MR PROCESS
1: Problem Definition
7
PROBLEM DEFINITION
It may be
8
The Process of Defining the Problem and Developing an Approach
Tasks involved
10
MR / MD PROBLEM
MD problem: asks what the decision maker wants to know- action
oriented- focuses on symptoms
MR problem : Asks what information is needed and how it should
be obtained – information oriented – focuses on the causes.
Joseph E.Seagram and Sons, Inc. was marketing a new wine and the VP [Mktg]
requested a survey of the US wine market.
15
RESEARCH DESIGN
Descriptive
Conclusive
Cross-sectional
Causal
16
Difference between Exploratory & Conclusive Research
EXPLORATORY CONCLUSIVE
QUALITATIVE RESEARCH
19
FOCUS GROUP
INTERVIEWS
20
Characteristics of Focus Group
It is an interview conducted by a trained moderator in a non-
structured and natural manner with a small group of
respondents.
Group Size 8 to 12
Group Composition homogeneous, respondents prescreened
Physical Setting relaxed, informal atmosphere
Time duration 1 –3 hrs
Moderator observational, interpersonal and
communication skills of the moderator.
21
EXPLORATORY RESEARCH TECHNIQUES
• Depth Interview
22
EXPLORATORY RESEARCH TECHNIQUES
Projective Techniques
• Association Technique- respondent is presented with
a stimulus and asked to respond with the first thing
that comes to mind.
Projective Techniques
• Completion Technique – Requires respondent to
complete an incomplete stimulus situation.
Sentence completion :
Godrej brand is my choice because _____________________
When it comes to shopping I __________________________
Titan is a brand for _________________________________
Story completion:
24
EXPLORATORY RESEARCH TECHNIQUES
Projective Techniques
Construction Technique - Respondents are required to construct a
response in the form of a dialogue / description.
Picture response :Thematic Appreciation test (TAT)- pictures
Cartoon tests:
Expressive Techniques
-visual/ verbal situations – relate feeling of
other people to the situation.
E.g. role play, third person test.
25
DESCRIPTIVE RESEARCH
A type of research used for describing market characteristics / functions.
E.g. percentage of heavy users of department stores
perception of product characteristics.
It requires a clarification of the 6Ws –
Who is target customer
What information to be attained
When to attain the information
Where to contact the respondents
Why are we obtaining these information
Way in which we are to get these information.
26
DESCRIPTIVE RESEARCH
CROSS-SECTIONAL LONGITUDINAL
27
DESCRIPTIVE RESEARCH
CROSS-SECTIONAL LONGITUDINAL
(collection of info from any
given sample only once)
28
SINGLE CROSS-SECTIONAL STUDY
AGE 1950
8-17 52.9 Sam
pl e 1
18-27 45.2
28-37 33.9
38-47 23.2
48+ 18.1
29
MULTIPLE CROSS-SECTIONAL STUDY
[COHORT ANALYSIS]
30
Single cross-sectional study
LONGITUDINAL STUDY
(collection of info. from a fixed sample of population element
measured repeatedly)
Findings :
• More golf events be shown in television
• Didn’t prefer reformulated version of men’s apparel
• Apparel should be attractive and functional
• Psychological factor associated with apparel
31
REL. ADVANTAGE & DISADVANTAGE OF
LONGITUDINAL & CROSS- SECTIONAL STUDY
A 200 200
B 300 300
C 500 500
A 100 50 50 200
(50%)
B 25 100 175 300
(33.33%)
C 75 150 275 500
(55%)
TOTAL 200 300 500 1000
TURNOVER TABLE / BRAND SWITCHING TABLE 33
Relative Advantages & Disadvantages of
Longitudinal & Cross-Sectional Designs
Note : + indicates a relative advantage over the other design; whereas – indicates a
relative disadvantage.
34
METHODS OF CONDUCTING DESCRIPTIVE
RESEARCH
35
SURVEY
36
37
OBSERVATION
STRUCTURED UNSTRUCTURED
Researcher specifies in details Researcher monitors all aspects
what is to be observed and how of the phenomena without
measurement are to be specifying details in advance
recorded.
Observer bias less Observer bias more. Findings
treated as hypothesis
Reliability data more Reliability data less
Used when problem has been Used when key component of
identified fully the problem has yet to be
formulated.
38
OBSERVATION
39
METHODS USED IN OBSERVATION METHOD
• PERSONAL
• MECHANICAL
• CONTENT ANALYSIS
• TRACE ANALYSIS
• AUDIT
40
CAUSAL RESEARCH
41
CONDITION FOR CAUSALITY
1. CONCOMITANT VARIATION – the extent to which cause (X) and effect (Y)
consideration.
before effect.
42
EXPERIMENTS
• LABORATORY / CONTROLLED
• NATURAL / FIELD
43
LABORATORY Vs. FIELD EXPT.
44
TEST MARKETING
45
THE MEASUREMENT PROCESS
46
NUMBER SYSTEM CHARACTERISTICS
• UNIQUE
• ORDER
• DIFFERENCE
• RATIO
47
TYPES OF SCALES
•NOMINAL SCALE
•ORDINAL SCALE
•INTERVAL SCALE
•RATIO SCALE
48
SCALE NUMBER SYSTEM MARKETING PERMISSIBLE
PHENOMENA STATISTICS
NOMINAL Unique definition of Brands Percentages
numerals (0,1,2,……..9) Male-Female Mode
Store Types Binomial test
Sale Territories Chi-square test
ORDINAL Order of numerals Attitudes Percentiles
(0<1<2<…<9) Preferences Median
Occupations Rank-Order
Social classes correlation
INTERVAL Equality of differences Attitudes Range
(2 –1 =7-6) Opinions Mean
Index numbers Standard Deviation
Product-Moment
Correlation
RATIO Equality of ratios (2 / 4 Ages Geometric Mean
= 4 / 8) Costs Harmonic Mean
Number of Coefficient of
customers variation
49
Sales (units/dollars)
MEASUREMENT SCALES
continuous itemized
stapel
50
PAIRED COMPARISON SCALING
Given below are 6 pairs of shampoo brands. Indicate which of the two
brands of shampoo in the pair you would prefer for personal use.
A B C
A 0 1
B 1 1
C 0 0
A
B
C
52
CONSTANT SUM SCALE
Allocate 100 points among the attributes based on the importance you
attach to each attribute.
Segment 1
Mildness 10
Price 20
Packaging 10
Fragrance 20
Moisturizing 10
Cleansing power 30
____
100 53
------
CONTINUOUS RATING
SCALE
How would you rate brand A as a soap?
54
Brand A is a high quality brand.
Strongly disagree
Disagree
Likert Scale
Neither agree nor disagree
Agree
Strongly agree
Strongly disagree
Disagree
Somewhat disagree Semantic-differential Scale
Neither agree nor disagree
Agree
Somewhat agree 55
Strongly agree
Brand A is a quality brand.
-1
-2
Stapel scale
-3
-4
-5
56
QUESIONNAIRE DESIGN PROCESS
Specify the information needed.
57
Eliminate bugs by pre-testing
Determine content of individual questions
58
Design questions to overcome the respondent’s inability
and unwillingness to answer.
IS RESPONDENT INFORMED?
Male member of the house may not be aware of the grocery expense per
month.
SENSITIVE INFORMATION
59
What is your monthly household income?
CHOOSING QUESTION STRUCTURE
UNSTRUCTURED QUESTION :
What are your intentions regarding purchasing a car?
STRUCTURED QUESTION :
• MULTIPLE CHOICE QUESTIONS –
Price Service
Quality Location
Location
Quantity of food
Ambience Quality
Service Price
61
•DICHOTOMOUS QUESTIONS:
Do you intend to buy a car in the next 6 months?
___________ Yes ___________ No
63
ERRORS
NON-SAMPLING ERROR :
Researcher Error ( surrogate , measurement, population
definition, data analysis error)
Interviewer Error (respondent selection, questioning,
recording, cheating error)
Respondent Error ( inability, unwillingness error)
64
SAMPLE DESIGN
SAMPLE VS CENSUS
SAMPLE CENSUS
Budget Small Large
Time available Short Long
Population size Large Small
Variance in characteristics Small Large
Cost of sampling errors Low High
Cost of non-sampling errors High Low
Nature of measurement Destructive Nondestructive
Attention to individual cases Yes No
65
SAMPLING
TECHNIQUES
NON
PROBABILITY
PROBABILITY
SIMPLE
CONVENIENCE JUDGEMENTAL QUOTA SNOWBALL SYSTEMATIC STRATIFIED CLUSTER
RANDOM
SAMPLING SAMPLING SAMPLING SAMPLING SAMPLING SAMPLING SAMPLING
SAMPLING
66
Convenience sampling
67
Judgmental sampling
5 10 15 20 25
68
Quota sampling
A B C D E It is a 2 stage restricted
judgmental sampling.
1 6 11 16 21
Stage 1: develop quota of
2 7 12 17 22
population elements
3 8 13 18 23 Stage 2: sample elements from
4 9 14 19 24 each quota are selected based on
convenience/ judgment.
5 10 15 20 25
69
Snowball sampling
70
PROBABILITY SAMPLING TECHNIQUES
Simple random sampling – each element in the population has a known and equal
probability of occurrence/ selection. A sampling frame is compiled and elements are
selected using random numbers.
A B C D E
1 6 11 16 21
2 7 12 17 22
3 8 13 18 23
4 9 14 19 24
5 10 15 20 25
71
SYSTEMATIC SAMPLING
The samples are chosen by selecting a random starting point and then
picking every i th element in succession from the sampling frame.
A B C D E
1 6 11 16 21
2 7 12 17 22
3 8 13 18 23
4 9 14 19 24
5 10 15 20 25
72
STRATIFIED SAMPLING
73
CLUSTER SAMPLING
The target population is divided into mutually exclusive and collectively exhaustive
sub-population called clusters. A random sample of clusters is selected based on
probability sampling technique. For each selected cluster , either all elements are
included or sample of elements are drawn probabilistically.
74
CHOOSING B/W PROBABILITY & NON-PROBABILITY SAMPLING
75
DATA ANALYSIS
Charts/ graphs
Frequency, mean, median, mode, deviation, covariance
Hypothesis testing
Correlation and Regression analysis
ANOVA/ ANCOVA
Cross-tabulation
Factor analysis
Cluster analysis
Conjoint analysis
Discriminant & Logit analysis
76
REPORT PREPARATION
1. Title page
2. Letter of authorization
3. Acknowledgement
4. Table of contents
5. List of tables/ graphs/ appendices
6. Executive summary
7. Problem definition
8. Approach to the problem
9. Research design
10. Data analysis
11. Results
12. Limitations
13. Recommendations and conclusion
14. Exhibit – questionnaire 77
15. Bibliography