Heterogeneous Logit Model Implications for Brand Positioning

Abstract

The author discusses the implications of a heterogeneous logit model for brand positioning. The methodology presented is a restricted version of a mixture-of-logits model and obtains brand positions on a product-market map and the distribution of preferences across households while accounting for the effects of marketing variables on household brand choice behavior. The restriction involves imposing a factor structure on the covariance matrix of the distribution of intrinsic brand preferences. An empirical application of the methodology is presented using A.C. Nielsen household-level scanner panel data on the purchases of liquid laundry detergents. The results indicate that the proposed model provides a better fit to the data than the unrestricted mixture-of-logits model or the Choice Map methodology.