Marketing Letters

, Volume 13, Issue 1, pp 17–25 | Cite as

Market Segment Derivation and Profiling Via a Finite Mixture Model Framework

  • Michel Wedel
  • Wayne S. Desarbo
Article

Abstract

The Marketing literature has shown how difficult it is to profile market segments derived with finite mixture models, especially using traditional descriptor variables (e.g., demographics). Such profiling is critical for the proper implementation of segmentation strategy. We propose a new finite mixture modelling approach that provides a variety of model specifications to address this segmentation dilemma. Our proposed approach allows for a large number of nested models (special cases) and associated tests of (local) independence to distinguish amongst them. A commercial application to customer satisfaction is provided where a variety of different model specifications are tested and compared.

finite mixture models market segmentation concomitant variables customer satisfaction 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Ainslie, Andrew, and Rossi, Peter. (1998). ''Brand Choice Across Multiple Categories: A Hierarchical Error Components Model,'' Marketing Science, 17(2) 91–106.Google Scholar
  2. Bozdogan, Hamparsum. (1987). ''Model Selection And Akaike's Information Criterion (AIC): The General Theory And Its Analytical Extensions,'' Psychometrika, 52, 345–370.Google Scholar
  3. Dayton, C. Mitchell, and McReady, George B., (1988). ''Concomitant Variable Latent Class Models,'' Journal of the American Statistical Association, 83, 173–178.Google Scholar
  4. DeSarbo, Wayne S., and Cron, William R., (1988). ''A Conditional Mixture Maximum Likelihood Methodology for Clusterwise Linear Regression,'' Journal of Classification, 5, 249–289.Google Scholar
  5. Dillon, William R., Ajith Kumar, A., and Smith de Borero, Melinda. (1993). ''Capturing Individual Differences in Paired Comparisons: An Extended BTL Model Incorporating Descriptor Variables,'' Journal of Marketing Research, 30, 42–51.Google Scholar
  6. Dillon, William R., and Mulani, Narenda. (1989). ''LADI: A Latent Discriminant Model for Analyzing Marketing Research Data,'' Journal of Marketing Research, 26, 15–29.Google Scholar
  7. Gupta, Sunil, and Chintagunta, Pradeep K. (1994). ''On Using Demographic Variables to Determine Segment Membership in Logit Mixture Models,'' Journal of Marketing Research, 31, 128–136.Google Scholar
  8. Jedidi, Kamel, Jagpa, Harsharanjeet S., and DeSarbo, Wayne S. (1997). ''Finite Mixture Structural Equation Models for Response-Based Segmentation and Unobserved Heterogeneity,'' Marketing Science, 16, 39–59.Google Scholar
  9. Kamakura, Wagner A., Wedel, Michel, and Agrawal, Jagdish. (1994). ''Concomitant Variable Latent Class Models for Conjoint Analysis,'' International Journal for Research in Marketing, 11, 451–464.Google Scholar
  10. Krieger, Abba M., and Green, Paul E. (1996). ''Modifying Cluster Based Segments to Enhance Agreement with an Exogenous Response Variable,'' Journal of Marketing Research, 33, 351–363.Google Scholar
  11. Wedel, Michel, and Kamakura, Wagner A. (2000). Market Segmentation: Conceptual and Methodological Foundations, Dordrecht: Kluwer.Google Scholar

Copyright information

© Kluwer Academic Publishers 2002

Authors and Affiliations

  • Michel Wedel
    • 1
  • Wayne S. Desarbo
    • 2
  1. 1.University of Groningen and University of MichiganUSA
  2. 2.Pennsylvania State University and Analytika Marketing Sciences, IncUSA

Personalised recommendations