Why and when multi-dimensional scaling technique can be applied
in marketing research?
Discuss.
Ans
- Which products do consumers see as similar to my product?
- Which products do consumers see as different from my product?
- Who are my customers?
- Who else should be my customers?
- What new products should I create?
Multidimensional
scaling (MDS) can be considered to be an alternative to factor analysis.
In general, the goal of the analysis is to detect meaningful underlying
dimensions that allow the researcher to explain observed similarities or
dissimilarities between the investigated objects. In factor analysis, the
similarities between objects (e.g. variables) are expressed in the correlation
matrix. With MDS one may analyse any kind of similarity or dissimilarity
matrix, in addition to correlation matrices.
This outcome is
visualised in a 2 dimensional map, which gives the researcher an immediate feel
of how differentiating the questions were. Questions which are clustered
together did get very similar scores by all respondents. This can be very
useful when optimising a questionnaire or to differentiate consumers based on
the most distinct questions.
Even though there are
similarities in the type of research questions to which MDS and factor analysis
can be applied, they are fundamentally different methods. Factor analysis
requires that the underlying data is distributed as multivariate normal, and
that the relationships are linear. MDS imposes no such restrictions. Just as
long as the rank-ordering similarities in the matrix are meaningful, MDS can be
used.
In terms of resultant
differences, factor analysis tends to extract more factors (dimensions) than
MDS; as a result, MDS often yields more readily, interpretable solutions. Most
importantly, however, MDS can be applied to any kind of similarities, while
factor analysis requires us to first compute a correlation matrix. MDS can be
based on subjects' direct assessment of similarities between stimuli, while
factor analysis requires subjects to rate those stimuli on some list of
attributes (for which the factor analysis is performed).
In summary, MDS methods
are applicable to a wide variety of research designs.
Multidimensional
scaling (MDS) analysis takes consumer judgments of similarity (or difference)
of pairs of products and produces a map of the perceived relationship among the
products. Each consumer evaluates the similarity (or difference) of each pair of
products. MDS determines the relative similarity perceived by consumers among
all the products. The results enable you to identify products that consumers
see as similar. The following are some of the questions that can be
answered with a multidimensional scaling analysis.
Multidimensional
Preference Analysis
In a conjoint analysis,
consumers indicate their preferences for products that are composed of
attributes. Sometimes in market research, the available data consist of
consumer preferences for products for which attributes are not defined.
Multidimensional preference analysis (MDPREF) is used to analyze such data.
MDPREF analysis is a principal component analysis of a data matrix with columns
that correspond to consumers and with rows that correspond to products. The
analysis results in a plot that reveals patterns of consumer preference for the
products. The following are some of the questions that can be answered with a
multidimensional preference analysis.
No comments:
Post a Comment