A Latent Structure Double Hurdle Regression Model for Exploring Heterogeneity in Consumer Search Patterns

Journal of Econometrics, Volume 89, Issues 1–2, Pages 423–455

Posted: 13 Jun 2016

See all articles by Wayne S. DeSarbo

Wayne S. DeSarbo

Pennsylvania State University

Jungwhan Choi

University of Michigan at Ann Arbor

Date Written: November 1999

Abstract

According to a vast behavioral literature in marketing, consumers typically engage in two sequential stages of information search in order to reduce uncertainty and maximize the anticipated benefits of a purchase. In the first stage, consumers initially retrieve product information stored in memory (internal search). If there is insufficient information in memory, the consumer then engages in external search for additional information from external stimuli in the market place. Consumers vary in the amount of each type of search they engage in depending upon their level of experience with the product category, socio-economic status, the importance of the purchase, product type, etc. This paper develops a latent structure methodology designed to model this sequential process. Here, the two sequential stages of search are explicitly modeled in a conditional, nested framework. In addition, heterogeneity in this process is accommodated vis á vis finite mixture distributions where distinct search groups or market segments can be identified via derived posterior probabilities of membership.

Keywords: Tobit Models, Consumer search, Finite mixtures, Latent structure analysis

Suggested Citation

DeSarbo, Wayne S. and Choi, Jungwhan, A Latent Structure Double Hurdle Regression Model for Exploring Heterogeneity in Consumer Search Patterns (November 1999). Journal of Econometrics, Volume 89, Issues 1–2, Pages 423–455, Available at SSRN: https://ssrn.com/abstract=2792345

Wayne S. DeSarbo (Contact Author)

Pennsylvania State University ( email )

University Park
State College, PA 16802
United States

Jungwhan Choi

University of Michigan at Ann Arbor

500 S. State Street
Ann Arbor, MI 48109
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Abstract Views
145
PlumX Metrics