This paper describes the estimation of a disaggregate joint- choice model for frequency, destination, and travel mode for shopping trips. The model builds on earlier research by Ben-Akiva in Transportation Research Record 526 that argued for the replacement of aggregate conditional (or sequential) model systems with disaggregate joint (or simultaneous) models and presented a model for the joint choice of destination and mode for shipping trips. The extension of this general model by use of the same multinomial logit form and a similar specification to include travel-frequency choice is an attempt to provide a more complete version of the joint-model structure. Estimation of the expanded joint-choice model proved to be feasible and resulted in behaviorally and statistically acceptable parameter values. All variables produced coefficients of the expected signs and magnitudes consistent with the behavioral notions on which the model specification was based. In general, the estimation of joint-choice models for travel demand was shown to be a computationally tractable alternative to the less acceptable conditional approaches that have been used in the past. An example of the application of the shopping model (combined with a previously estimated modal-choice model for work trips) to the evaluation of transportation policy options is used to highlight some of the features of both the particular models used and the general modeling approach that they represent.

Media Info

  • Media Type: Print
  • Features: Figures; References; Tables;
  • Pagination: pp 136-150
  • Monograph Title: New approaches to travel forecasting
  • Serial:

Subject/Index Terms

Filing Info

  • Accession Number: 00141297
  • Record Type: Publication
  • ISBN: 030902482X
  • Files: TRIS, TRB
  • Created Date: Oct 26 1976 12:00AM