WORKSHOP ON MATHEMATICAL STRUCTURES AND UNCERTAINTY. EVALUATION OF DISCRETE-CHOICE RANDOM-UTILITY MODELS AS PRACTICAL TOOLS OF TRANSPORTATION SYSTEMS ANALYSIS

Travel decisions frequently entail choices among discrete sets of alternatives such as frequencies, Destinations, modes and routes of travel. A large proportion of travel behavior research and practical travel demand analysis is oriented toward predicting the outcomes of such choices. A behavioral and mathematical framework for modeling these choices is provided by a class of mathematical models called discrete-choice random-utility models. Their advantages enable random-utility models to forecast travel demand more accurately and less expensively than do other models. This paper reviews current knowledge of random-utility modeling that affects practical travel demand analysis and identifies the implications of this knowledge for practice. The remainder of the paper consists of (1) review of the main concepts underlying random-utility models and summary of the methods normally used for developing empirical models; (2) evaluation of initially claimed advantages of random-utility models; and (3) discussion of additional issues that have arisen. The behavioral basis of random utility models and practical benefits associated therewith have been exaggerated. Their validity remains uncertain, and even if valid, does not guarantee that potentially serious errors. Several recent improvements potentially serious errors. Several recent improvements in the modeling will be ready for widespread application as soon as software for them becomes available. There are a variety of unsolved problems affecting practical application of random-utility models, involving such matters as alternative decision processes, geographical transferrability, predictability of demand for new alternatives, computational procedures for equilibrium travel demand/transport system performance, and relative merits of choice-based and exogenous sample designs.

• Record URL:
  • http://onlinepubs.trb.org/Onlinepubs/sr/sr201/sr201-026.pdf
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/0360859X
• Supplemental Notes:
  • Proceedings of a conference held October 3-7, 1982, Easton, Maryland. Distribution, posting, or copying of this PDF is strictly prohibited without written permission of the Transportation Research Board of the National Academy of Sciences. Unless otherwise indicated, all materials in this PDF are copyrighted by the National Academy of Sciences. Copyright © National Academy of Sciences. All rights reserved.
• Corporate Authors:

  Transportation Research Board

  500 Fifth Street, NW
  Washington, DC  United States  20001
• Authors:
  • Horowitz, Joel
• Publication Date: 1984

Media Info

• Media Type: Digital/other
• Features: References;
• Pagination: pp 127-136
• Serial:
  • Transportation Research Board Special Report
  • Issue Number: 201
  • Publisher: Transportation Research Board
  • ISSN: 0360-859X

Subject/Index Terms

• TRT Terms: Behavior; Mathematical models; Mode choice; Routing; Stochastic processes; Travel behavior; Travel demand
• Old TRIS Terms: Modal selection
• Subject Areas: Data and Information Technology; Highways; Planning and Forecasting; Public Transportation; I72: Traffic and Transport Planning;

Filing Info

• Accession Number: 00390212
• Record Type: Publication
• Files: TRIS, TRB, ATRI
• Created Date: Oct 30 1984 12:00AM