Accommodating a Flexible Response Heterogeneity Distribution in Choice Models of Human Behavior for Transportation Planning

In this project, the research team will formulate a copula-based framework to accommodate non-normal continuous mixing distributions in the multinomial probit (MNP) model. This approach will allow a multivariate mixing distribution that can combine any continuous distributional shape for each coefficient, including (but not limited to) the skew-normal distribution. The procedure will be based on generating a multivariate continuous distribution through the use of specified parametric univariate continuous coefficient distributions (that can be different for different coefficients) combined with a Gaussian Copula. This research will also propose two alternative estimation procedures for the new model. The effectiveness of the formulation and inference approach will be demonstrated through simulations and an empirical application.

Language

• English

Project

• Status: Completed
• Sponsor Organizations:

  Office of the Assistant Secretary for Research and Technology

  University Transportation Centers Program
  Department of Transportation
  Washington, DC  United States  20590
• Project Managers:

  Bhat, Chandra

• Performing Organizations:

  Data-Supported Transportation Operations and Planning Center

  University of Texas at Austin
  Austin, TX  United States  78701
• Principal Investigators:

  Bhat, Chandra

• Start Date: 20160501
• Expected Completion Date: 20171231
• Actual Completion Date: 0
• Source Data: 131

Subject/Index Terms

• TRT Terms: Behavior; Choice models; Empirical methods; Estimation theory; Probits; Simulation; Transportation planning
• Subject Areas: Planning and Forecasting; Transportation (General);

Filing Info

• Accession Number: 01611898
• Record Type: Research project
• Source Agency: Data-Supported Transportation Operations and Planning Center
• Files: UTC, RIP
• Created Date: Sep 23 2016 2:50PM