The Estimation of Multinomial Probit Models: A New Calibration Algorithm

Transportation Science, Vol. 23, No.4, November 1989

13 Pages Posted: 24 Apr 2014

Date Written: 1989

Abstract

This study proposes the estimation of Multinomial Probit models using Mendell-Elston's approximation to the cumulative multivariate normal for the computation of choice probabilities. The accuracy of this numerical approximation in computing probabilities is compared with other procedures used in existing calibration programs. Finally, the proposed estimation procedure is tested on simulated choice data.

Suggested Citation

Kamakura, Wagner A., The Estimation of Multinomial Probit Models: A New Calibration Algorithm (1989). Transportation Science, Vol. 23, No.4, November 1989, Available at SSRN: https://ssrn.com/abstract=2428339

Wagner A. Kamakura (Contact Author)

Rice University ( email )

6100 South Main Street
P.O. Box 1892
Houston, TX 77005-1892
United States
(713) 348-6307 (Phone)

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
14
Abstract Views
283
PlumX Metrics