Mixed Logit Mode Choice Model Using Panel Data: Accounting for Systematic and Random Variations in Responses and Preferences

Travel demand models are usually estimated using cross-sectional data. The increased need of understanding variability in travel behavior and the parallel advances in travel demand modeling techniques has recently brought to the re-discovery of panel data. The most recent works on panel data are based on multi-week travel diary, where a number of households recorded all their daily trips continuatively over a certain number of weeks. In this paper, we use the six weeks panel data from Mobidrive survey to estimate mode choice model that accounts for systematic and random heterogeneity over individual preferences and responses, and correlation across individual over three time periods: the single day, the single week, the days of week (all Monday in the wave, and so on), and correlation across individuals and members of the families over the six weeks. We also analyze the effect on modeling results of the day-to-day variation and the repeated behaviors over time. The results suggest that individual tastes for time and cost, and in particular the SVT point estimates, are fairly stable across the sequence-day but there is a significant systematic and random heterogeneity around these mean values and in the preferences for the different alternatives. The study found that accounting for correlation over individual improves model results, however the degree of the correlation and its effect on the significance of systematic and heterogeneity differs over the time periods considered. Moreover, the improvement in model estimates achieved by accounting for correlation across individuals is to a great extent given by persistent behaviors.

Language

  • English

Media Info

  • Media Type: DVD
  • Features: Figures; References; Tables;
  • Pagination: 20p
  • Monograph Title: TRB 87th Annual Meeting Compendium of Papers DVD

Subject/Index Terms

Filing Info

  • Accession Number: 01100458
  • Record Type: Publication
  • Report/Paper Numbers: 08-0806
  • Files: TRIS, TRB
  • Created Date: Jun 3 2008 7:26AM