Marketing Research

advertisement
Marketing Research
Aaker, Kumar, Day
Ninth Edition
Instructor’s Presentation Slides
1
Chapter Twenty-two
Multidimensional Scaling and
Conjoint Analysis
Marketing Research 9th Edition
Aaker, Kumar, Day
2
http://www.drvkumar.com/mr9/
Multidimensional Scaling
Used to:
 Identify dimensions by which objects are perceived or
evaluated
 Position the objects with respect to those dimensions
 Make positioning decisions for new and old products
Marketing Research 9th Edition
Aaker, Kumar, Day
3
http://www.drvkumar.com/mr9/
Approaches To Creating Perceptual Maps
Perceptual map
Attribute data
Nonattribute
data
Similarity
Factor
analysis
Marketing Research 9th Edition
Aaker, Kumar, Day
Correspondence
analysis
Discriminant
analysis
4
Preference
MDS
http://www.drvkumar.com/mr9/
Attribute Based Approaches
 Attribute based MDS - MDS used on attribute data
 Assumption
 The attributes on which the individuals' perceptions of objects are
based can be identified
 Methods used to reduce the attributes to a small number of dimensions
 Factor Analysis
 Discriminant Analysis
 Limitations
 Ignore the relative importance of particular attributes to customers
 Variables are assumed to be intervally scaled and continuous
Marketing Research 9th Edition
Aaker, Kumar, Day
5
http://www.drvkumar.com/mr9/
Comparison of Factor and Discriminant
Analysis
Factor Analysis
Discriminant Analysis
 Groups attributes that are
similar
 Identifies clusters of
attributes on which objects
differ
 Identifies a perceptual
dimension even if it is
represented by a single
attribute
 Based on both perceived
differences between objects
and differences between
people's perceptions of
objects
 Statistical test with null
hypothesis that two objects
are perceived identically
 Dimensions provide more
interpretive value than
discriminant analysis
Marketing Research 9th Edition
Aaker, Kumar, Day
6
http://www.drvkumar.com/mr9/
Perceptual Map of a Beverage Market
Marketing Research 9th Edition
Aaker, Kumar, Day
7
http://www.drvkumar.com/mr9/
Perceptual Map of Pain Relievers
Gentleness
. Tylenol
. Bufferin
Effectiveness
. Bayer
. Private-label
aspirin
Marketing Research 9th Edition
Aaker, Kumar, Day
. Advil
. Nuprin
. Anacin
. Excedrin
8
http://www.drvkumar.com/mr9/
Basic Concepts of Multidimensional Scaling
(MDS)
 MDS uses proximities ( value which denotes how similar or how
different two objects are perceived to be) among different objects as
input
 Proximities data is used to produce a geometric configuration of
points (objects) in a two-dimensional space as output
 The fit between the derived distances and the two proximities in each
dimension is evaluated through a measure called stress
 The appropriate number of dimensions required to locate objects can
be obtained by plotting stress values against the number of
dimensions
Marketing Research 9th Edition
Aaker, Kumar, Day
9
http://www.drvkumar.com/mr9/
Determining Number of Dimensions
Due to large increase in the stress values from two dimensions to
one, two dimensions are acceptable
Marketing Research 9th Edition
Aaker, Kumar, Day
10
http://www.drvkumar.com/mr9/
Attribute-based MDS
Advantages
 Attributes can have diagnostic and operational value
 Attribute data is easier for the respondents to use
 Dimensions based on attribute data predicted preference
better as compared to non-attribute data
Marketing Research 9th Edition
Aaker, Kumar, Day
11
http://www.drvkumar.com/mr9/
Attribute-based MDS (contd.)
Disadvantages
 If the list of attributes is not accurate and complete, the study
will suffer
 Respondents may not perceive or evaluate objects in terms of
underlying attributes
 May require more dimensions to represent them than the use of
flexible models
Marketing Research 9th Edition
Aaker, Kumar, Day
12
http://www.drvkumar.com/mr9/
Application of MDS With Nonattribute Data
Similarity Data
 Reflect the perceived similarity of two objects from the
respondents' perspective
 Perceptual map is obtained from the average similarity ratings
 Able to find the smallest number of dimensions for which there is
a reasonably good fit between the input similarity rankings and
the rankings of the distance between objects in the resulting
space
Marketing Research 9th Edition
Aaker, Kumar, Day
13
http://www.drvkumar.com/mr9/
Similarity Judgments
Marketing Research 9th Edition
Aaker, Kumar, Day
14
http://www.drvkumar.com/mr9/
Perceptual Map Using Similarity Data
Marketing Research 9th Edition
Aaker, Kumar, Day
15
http://www.drvkumar.com/mr9/
Application of MDS With Nonattribute
Data (Contd.)
Preference Data
 An ideal object is the combination of all customers' preferred
attribute levels
 Location of ideal objects is to identify segments of customers
who have similar ideal objects, since customer preferences
are always heterogeneous
Marketing Research 9th Edition
Aaker, Kumar, Day
16
http://www.drvkumar.com/mr9/
Issues in MDS
 Perceptual mapping has not been shown to be reliable across
different methods
 The effect of market events on perceptual maps cannot be
ascertained
 The interpretation of dimensions is difficult
 When more than two or three dimensions are needed,
usefulness is reduced
Marketing Research 9th Edition
Aaker, Kumar, Day
17
http://www.drvkumar.com/mr9/
Conjoint Analysis
 Technique that allows a subset of the possible
combinations of product features to be used to determine
the relative importance of each feature in the purchase
decision
Marketing Research 9th Edition
Aaker, Kumar, Day
18
http://www.drvkumar.com/mr9/
Conjoint Analysis
 Used to determine the relative importance of various
attributes to respondents, based on their making trade-off
judgments
 Uses:
 To select features on a new product/service
 Predict sales
 Understand relationships
Marketing Research 9th Edition
Aaker, Kumar, Day
19
http://www.drvkumar.com/mr9/
Inputs in Conjoint Analysis
 The dependent variable is the preference judgment that a
respondent makes about a new concept
 The independent variables are the attribute levels that need to
be specified
 Respondents make judgments about the concept either by
considering
 Two attributes at a time - Trade-off approach
 Full profile of attributes - Full profile approach
Marketing Research 9th Edition
Aaker, Kumar, Day
20
http://www.drvkumar.com/mr9/
Outputs in Conjoint Analysis
 A value of relative utility is assigned to each level of an attribute
called partworth utilities
 The combination with the highest utilities should be the one that
is most preferred
 The combination with the lowest total utility is the least
preferred
Marketing Research 9th Edition
Aaker, Kumar, Day
21
http://www.drvkumar.com/mr9/
Applications of Conjoint Analysis
 Where the alternative products or services have a number
of attributes, each with two or more levels
 Where most of the feasible combinations of attribute levels
do not presently exist
 Where the range of possible attribute levels can be
expanded beyond those presently available
 Where the general direction of attribute preference
probably is known
Marketing Research 9th Edition
Aaker, Kumar, Day
22
http://www.drvkumar.com/mr9/
Steps in Conjoint Analysis
1.
Choose product attributes (e.g. size, price, model)
2.
Choose the values or options for each attribute
3.
Define products as a combination of attribute options
4.
A value of relative utility is assigned to each level of an attribute
called partworth utilities
5.
The combination with the highest utilities should be the one that
is most preferred
Marketing Research 9th Edition
Aaker, Kumar, Day
23
http://www.drvkumar.com/mr9/
Utilities for Credit Card Attributes
Source: Paul E. Green, ‘‘A New Approach to Market Segmentation,’’
Marketing Research 9th Edition
Aaker, Kumar, Day
24
http://www.drvkumar.com/mr9/
Utilities for Credit Card Attributes
(contd.)
Marketing Research 9th Edition
Aaker, Kumar, Day
25
http://www.drvkumar.com/mr9/
Full-profile and Trade-off Approaches
Source: Adapted from Dick Westwood, Tony Lunn, and David Bezaley, ‘‘The Trade-off Model and Its Extensions’’
Marketing Research 9th Edition
26
http://www.drvkumar.com/mr9/
Aaker, Kumar, Day
Conjoint Analysis - Example
Marketing Research 9th Edition
Aaker, Kumar, Day
Make
Price
MPG
Door
0
Domestic
$22,000
22
2-DR
1
Foreign
$18,000
27
28
4-DR
http://www.drvkumar.com/mr9/
Conjoint Analysis – Regression Output
Model Summary
Model
1
R
Adjusted
R Square
R Square
.785 b
c
.616
Std. Error of
the Es timate
.488
6.921
b. Predictors: D oor, MPG, Price, Make
c. Dependent Variable: Rank
ANOVA c
Sum of
Squares
Model
1
df
Mean Square
Regress ion
921.200
4
230.300
Residual
574.800
12
47.900
1496.000
16
Total
F
Sig.
.015 a
4.808
a. Predictors: D oor, MPG, Price, Make
c. Dependent Variable: Rank
Coefficients
Unstandardized
Coefficients
Model
1
Marketing Research 9th Edition
Aaker, Kumar, Day
B
Std. Error
a,b
Standardized
Coefficients
Beta
t
Sig.
Make
1.200
3.095
.088
.388
.705
Price
4.200
3.095
.307
1.357
.200
MPG
5.200
3.095
.380
1.680
.119
Door
2.700
3.095
.197
.872
.400
a. Dependent Variable: Rank
28
b. Linear Regression through the Origin
http://www.drvkumar.com/mr9/
Part-worth Utilities
1.4
4.5
1.2
4
3.5
3
Utility
Utility
1
0.8
0.6
2.5
2
1.5
0.4
1
0.5
0.2
0
0
Foreign
Domestic
18,000
Make
Price
3
6
2.5
5
2
Utility
4
Utility
22,000
3
1.5
1
2
0.5
1
0
0
28
4-Dr
22
Door
MPG
Marketing Research 9th Edition
Aaker, Kumar, Day
2-Dr
29
http://www.drvkumar.com/mr9/
Relative Importance of Attributes
Attribute
Make
Part-worth Utility
1.2
Relative
Importance
9%
Price
4.2
32%
MPG
5.2
39%
Door
2.7
20%
Marketing Research 9th Edition
Aaker, Kumar, Day
30
http://www.drvkumar.com/mr9/
Limitations of Conjoint Analysis
Trade-off approach
 The task is too unrealistic
 Trade-off judgments are being made on two attributes,
holding the others constant
Full-profile approach
 If there are multiple attributes and attribute levels, the task
can get very demanding
Marketing Research 9th Edition
Aaker, Kumar, Day
31
http://www.drvkumar.com/mr9/
Download