MODELING MULTIPLE SOURCES OF HETEROGENEITY IN MODE CHOICE MODEL

This paper is to compare the difference of heterogeneous effect caused by multiple sources, including unobserved heterogeneity in alternatives, taste variation, and heterogeneous choice sets. We construct several heterogeneous discrete choice models to conduct with various heterogeneities. A stated preference data of intercity travel choice is used as empirical case. The empirical results show that the mixed logit model conducting with taste variation has better explanatory power in single heterogeneity and heterogeneous competing destinations model integrating multiple heterogeneities has the best explanatory power. If we ignore heterogeneity in constructing discrete choice models, the estimation of value of time will be biased. Sensitivity analysis presents that expensive alternatives, like air mode, should adopt cut-price strategy to increase choice share and inexpensive alternatives, like bus and train mode, should improve the level of service in travel time to increase choice share.

[1]  A. Fotheringham.  Note---Consumer Store Choice and Choice Set Definition , 1988 .

[2]  Gary J. Russell,et al.  A Probabilistic Choice Model for Market Segmentation and Elasticity Structure , 1989 .

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

[4]  Pradeep K. Chintagunta,et al.  Heterogeneous Logit Model Implications for Brand Positioning , 1994 .

[5]  K. Train.  Discrete Choice Methods with Simulation , 2003 .

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

[7]  Cheng Hsiao,et al.  Analysis of Panel Data , 1987 .

[8]  Pradeep Chintagunta.  Measuring the effects of new brand introduction on inter-brand strategic interaction , 1999, Eur. J. Oper. Res..

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

[10]  K. Train,et al.  Forecasting new product penetration with flexible substitution patterns , 1998 .

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

[12]  Ajay K. Manrai,et al.  Two-stage discrete choice models for scanner panel data: An assessment of process and assumptions , 1998, Eur. J. Oper. Res..

[13]  P. Doyle,et al.  Random utility models in marketing research: a survey , 2001 .

[14]  C. Bhat.  Quasi-random maximum simulated likelihood estimation of the mixed multinomial logit model , 2001 .

[15]  David A. Hensher,et al.  A latent class model for discrete choice analysis: contrasts with mixed logit , 2003 .

[16]  Juan de Dios Ortúzar,et al.  Representation of heteroskedasticity in discrete choice models , 2000 .

[17]  Chandra R. Bhat,et al.  An Endogenous Segmentation Mode Choice Model with an Application to Intercity Travel , 1997, Transp. Sci..

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

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