login

Removing Heterogeneity Bias from Logit Model Estimation

Marketing SciencePublished 1 February 1988
J. Morgan Jones, Jane Talmage Landwehr
Citations92
SJR quartileQ1
SJR score7.54
SNIP2.65

Abstract

This paper introduces a new estimation procedure for the logit model that is an extension of a conditional estimation procedure developed by Chamberlain (Chamberlain, G. 1978. On the use of panel data. Working paper, Harvard University, 1–52; Chamberlain, G. 1980. Analysis of covariance with qualitative data. Rev. Econom. Stud. 47 225–238.). The method eliminates heterogeneity bias which is present in the estimates produced by traditional estimation techniques. It improves the goodness of fit and explanatory power of these models, while incorporating purchase event feedback.

Keywords

Economics, Econometrics and FinanceBusiness, Management and Accounting