DRAFT Identification of the Logit Kernel ( or Mixed Logit ) Model

Logit Kernel is a discrete choice model that has both probit-like disturbances as well as an additive i.i.d. extreme value (or Gumbel) disturbance à la multinomial logit. The result is an intuitive, practical, and powerful model that combines the flexibility of probit (and more) with the tractability of logit. For this reason, logit kernel has been deemed the “model of the future” and is becoming extremely popular in the literature. It has been included in popular statistical software packages as well as a recent edition of a widely used econometrics textbook and two texts specializing on discrete choice. While the basic structure of logit kernel models is well understood, there are important identification issues that are often overlooked. Misunderstanding of these issues can lead to biased estimates as well as a significant loss of fit. This paper presents a general framework for identifying the logit kernel model. Many of the special cases of the logit kernel model are discussed in detail, including heteroscedasticity, error components, nesting structures, random coefficients, auto correlation, and application to panel data. Specification and identification issues related to each special case are identified. Finally the findings are demonstrated with empirical examples using both simulated and real data. The objectives of the paper are to present our specific findings, as well as highlight the broader themes and provide tools for uncovering identification issues pertaining to logit kernel models. Introduction The logit kernel model is a straightforward concept: it is a discrete choice model in which the disturbances (of the utilities) consist of both a probit-like portion and an additive i.i.d. Gumbel portion (i.e., a multinomial logit disturbance). Multinomial logit (MNL) has its well-known blessing of tractability and its equally well-known curse of a rigid error structure leading to the IIA property. The nested logit model relaxes the rigidity of the MNL error structure and has the advantage of retaining a probability function in closed form. Nonetheless, nested logit is still limited and cannot capture many forms of unobserved heterogeneity, including, for example, random taste heterogeneity. The logit kernel model with its probit-like (but even more general) disturbances completely opens up the specification of the disturbances so that almost any desirable error structure can be represented in

[1]  Füsun F. Gönül,et al.  Modeling Multiple Sources of Heterogeneity in Multinomial Logit Models: Methodological and Managerial Issues , 1993 .

[2]  M. Ben-Akiva,et al.  The demand for local telephone service: a fully discrete model of residential calling patterns and service choices , 1987 .

[3]  Chandra R. Bhat,et al.  Accommodating variations in responsiveness to level-of-service measures in travel mode choice modeling , 1998 .

[4]  K. Train,et al.  Mixed Logit with Repeated Choices: Households' Choices of Appliance Efficiency Level , 1998, Review of Economics and Statistics.

[5]  C. Bhat.  A heteroscedastic extreme value model of intercity travel mode choice , 1995 .

[6]  K. Train,et al.  Joint mixed logit models of stated and revealed preferences for alternative-fuel vehicles , 1999, Controlling Automobile Air Pollution.

[7]  D. McFadden,et al.  MIXED MNL MODELS FOR DISCRETE RESPONSE , 2000 .

[8]  Kenneth Train,et al.  Customers' Choice Among Retail Energy Suppliers: The Willingness-to-Pay for Service Attributes , 2000 .

[9]  Shlomo Bekhor,et al.  Adaptation of Logit Kernel to Route Choice Situation , 2002 .

[10]  Joel H. Steckel,et al.  A Heterogeneous Conditional Logit Model of Choice , 1988 .

[11]  D. S. Bunch,et al.  Estimability in the Multinomial Probit Model , 1989 .

[12]  Chandra R. Bhat,et al.  ACCOMMODATING FLEXIBLE SUBSTITUTION PATTERNS IN MULTI-DIMENSIONAL CHOICE MODELING: FORMULATION AND APPLICATION TO TRAVEL MODE AND DEPARTURE TIME CHOICE , 1998 .

[13]  C. Bhat,et al.  A Mixed Multinomial Logit Model Analysis of Weekend Recreational Episode Type Choice , 2004 .

[14]  Karthik K. Srinivasan,et al.  A Dynamic Kernel Logit Model for the Analysis of Longitudinal Discrete Choice Data: Properties and Computational Assessment , 2005, Transp. Sci..

[15]  Moshe Ben-Akiva,et al.  Discrete Choice Analysis: Theory and Application to Travel Demand , 1985 .

[16]  Joan L. Walker.  Mixed Logit (or Logit Kernel) Model: Dispelling Misconceptions of Identification , 2002 .

[17]  K. Train.  Recreation Demand Models with Taste Differences Over People , 1998 .

[18]  Joan L. Walker.  Extended discrete choice models : integrated framework, flexible error structures, and latent variables , 2001 .

[19]  D. McFadden.  Econometric analysis of qualitative response models , 1984 .

[20]  Moshe Ben-Akiva,et al.  DRAFT Specification , Identification , & Estimation of the Logit Kernel ( or Continuous Mixed Logit ) Model * , 2001 .

[21]  Mark Hansen,et al.  Analysis of Discrete Choice Data with Repeated Observations: Comparison of Three Techniques in Intercity Travel Case , 1997 .

[22]  M. Sobel,et al.  Identification Problems in the Social Sciences. , 1996 .

[23]  Joel Huber,et al.  Customer-Specific Taste Parameters and Mixed Logit , 1999 .