A practical test for the choice of mixing distribution in discrete choice models

被引:81
作者
Fosgerau, Mogens [1 ]
Bierlaire, Michel [1 ]
机构
[1] Ecole Polytech Fed Lausanne, Transport & Mobil Lab, Lausanne, Switzerland
关键词
mixed logit; random parameters; nonparametric; seminonparametric; hypothesis testing;
D O I
10.1016/j.trb.2007.01.002
中图分类号
F [经济];
学科分类号
02 ;
摘要
The choice of a specific distribution for random parameters of discrete choice models is a critical issue in transportation analysis. Indeed, various pieces of research have demonstrated that an inappropriate choice of the distribution may lead to serious bias in model forecast and in the estimated means of random parameters. In this paper, we propose a practical test, based on seminonparametric techniques. The test is analyzed both on synthetic and real data, and is shown to be simple and powerful. (c) 2007 Elsevier Ltd. All rights reserved.
引用
收藏
页码:784 / 794
页数:11
相关论文
共 36 条
[11]  
BURGE P, 2004, P EUR TRANSP C
[12]  
CARRIER E, 2003, THESIS MIT
[13]  
Doornik JA, 2001, OX OBJECT ORIENTED M
[14]  
FOSGERAU M, 2005, EUROPEAN TRANSPORT C
[15]  
FOSGERAU M, UNPUB TRANSPORTATI A
[16]   Investigating the distribution of the value of travel time savings [J].
Fosgerau, Mogens .
TRANSPORTATION RESEARCH PART B-METHODOLOGICAL, 2006, 40 (08) :688-707
[17]   Capturing correlation with subnetworks in route choice models [J].
Frejinger, E. ;
Blerlaire, M. .
TRANSPORTATION RESEARCH PART B-METHODOLOGICAL, 2007, 41 (03) :363-378
[18]   SEMI-NONPARAMETRIC MAXIMUM-LIKELIHOOD-ESTIMATION [J].
GALLANT, AR ;
NYCHKA, DW .
ECONOMETRICA, 1987, 55 (02) :363-390
[19]   Accounting for heterogeneity in the variance of unobserved effects in mixed logit models [J].
Greene, WH ;
Hensher, DA ;
Rose, J .
TRANSPORTATION RESEARCH PART B-METHODOLOGICAL, 2006, 40 (01) :75-92
[20]  
HAN B, 2001, 8 ANN M TRANSP RES B