A latent class model for discrete choice analysis: contrasts with mixed logit

William Greene and David Hensher

Transportation Research Part B: Methodological, 2003, vol. 37, issue 8, 681-698

Abstract: The multinomial logit model (MNL) has for many years provided the fundamental platform for the analysis of discrete choice. The basic model's several shortcomings, most notably its inherent assumption of independence from irrelevant alternatives have motivated researchers to develop a variety of alternative formulations. The mixed logit model stands as one of the most significant of these extensions. This paper proposes a semi-parametric extension of the MNL, based on the latent class formulation, which resembles the mixed logit model but which relaxes its requirement that the analyst makes specific assumptions about the distributions of parameters across individuals. An application of the model to the choice of long distance travel by three road types (2-lane, 4-lane without a median and 4-lane with a median) by car in New Zealand is used to compare the MNL latent class model with mixed logit.

Date: 2003
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (675)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0191-2615(02)00046-2
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:transb:v:37:y:2003:i:8:p:681-698

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/supportfaq.cws_home/regional
https://shop.elsevie ... _01_ooc_1&version=01

Access Statistics for this article

Transportation Research Part B: Methodological is currently edited by Fred Mannering

More articles in Transportation Research Part B: Methodological from Elsevier
Bibliographic data for series maintained by Catherine Liu ().