Affordable Access

Access to the full text

Comparative study on mode split discrete choice models

Authors
  • Chen, Xianlong1
  • Liu, Xiaoqian2
  • Li, Fazhi3
  • 1 Guangzhou Transport Planning and Research Institute, 11th Floor, No. 80 of Jixiang Road, Guangzhou, 510030, China , Guangzhou (China)
  • 2 Architectural Design & Research Institute of Tongji University (Group) Co., Ltd., Transportation Planning and Design Division, Shanghai, 200092, China , Shanghai (China)
  • 3 Guangzhou Transport Planning and Research Institute, Guangzhou, 510030, China , Guangzhou (China)
Type
Published Article
Journal
Journal of Modern Transportation
Publisher
Springer Berlin Heidelberg
Publication Date
Dec 20, 2013
Volume
21
Issue
4
Pages
266–272
Identifiers
DOI: 10.1007/s40534-013-0028-5
Source
Springer Nature
Keywords
License
Green

Abstract

Discrete choice model acts as one of the most important tools for studies involving mode split in the context of transport demand forecast. As different types of discrete choice models display their merits and restrictions diversely, how to properly select the specific type among discrete choice models for realistic application still remains to be a tough problem. In this article, five typical discrete choice models for transport mode split are, respectively, discussed, which includes multinomial logit model, nested logit model (NL), heteroscedastic extreme value model, multinominal probit model and mixed multinomial logit model (MMNL). The theoretical basis and application attributes of these five models are especially analysed with great attention, and they are also applied to a realistic intercity case of mode split forecast, which results indicating that NL model does well in accommodating similarity and heterogeneity across alternatives, while MMNL model serves as the most effective method for mode choice prediction since it shows the highest reliability with the least significant prediction errors and even outperforms the other four models in solving the heterogeneity and similarity problems. This study indicates that conclusions derived from a single discrete choice model are not reliable, and it is better to choose the proper model based on its characteristics.

Report this publication

Statistics

Seen <100 times