CONSIDERATION SETS IN CONJOINT-ANALYSIS

The authors model product consideration as preceding choice in a segme nt-level conjoint model. They propose a latent-class tobit model to es timate cardinal, segment-level preference functions based on consumers ' preference ratings for product concepts considered worth adding to c onsumers' self-explicated consideration sets. The probability with whi ch the utility of a product profile exceeds an unobserved threshold co rresponds to its consideration probability, which is assumed to be ind ependent across product profiles and common to consumers in a segment. A market-share simulation compares the predictions of the proposed mo del with those obtained from an individual-level tobit model and from traditional ratings-based conjoint analysis. The authors also report s imulations that assess the robustness of the proposed estimation proce dure, which uses an E-M algorithm to obtain maximum likelihood paramet er estimates.