Bayesian prediction in hybrid conjoint analysis

F ter Hofstede*, Y Kim, M Wedel

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

23 Citations (Scopus)

Abstract

The authors propose a general model that includes the effects of discrete and continuous heterogeneity as well as self-stated and derived attribute importance in hybrid conjoint studies. Rather than use the self-stated importances as prior information, as has been done in several previous approaches, the authors consider them data and therefore include them in the formulation of the likelihood, which helps investigate the relationship of self-stated and derived importances at the individual level. The authors formulate several special cases of the model and estimate them using the Gibbs sampler. The authors reanalyze Srinivasan and Park's (1997) data and show that the current model predicts real choices better than competing models do. The posterior credible intervals of the predictions of models with the different heterogeneity specifications overlap, so there is no clear superior specification of heterogeneity. However, when different sources of data are used-that is, full profile evaluations, self-stated importances, or both-clear differences arise in the accuracy of predictions. Moreover, the authors find that including the self-stated importances in the likelihood leads to much better predictions than does considering them prior information.

Original languageEnglish
Pages (from-to)253-261
Number of pages9
JournalJournal of Marketing Research
Volume39
Issue number2
Publication statusPublished - May-2002

Keywords

  • MARKETS
  • MODELS

Cite this