Modeling Discrete Choices in the Presence of Inertia and Serial Correlation

The authors discuss two problems in transportation policy measure response modeling. In the context of travel behavior change reluctance, the concept of inertia or habit remains unresolved. And over time by a given individual, there may be dependence or correlation between the choices he or she makes, a concept known as serial correlation. There is a close relationship between the two phenomena. The authors discuss how serial correlation and inertia consideration influence travel choice. The authors allow for serial correlation and incorporate randomly distributed inertia thresholds when they formulate a fairly general discrete choice model. An individual's choice conditions and socioeconomic characteristics may result in inertia threshold as a function. Model application can occur with stated preference, mixed revealed, and panel data. The authors confirm that serious model prediction and estimation errors may arise, especially in large policy impact cases, if such phenomena are not considered when they exist in the population.

  • Availability:
  • Authors:
    • Cantillo, Victor
    • Ortuzar, Juan de Dios
    • Williams, Huw C W L
  • Publication Date: 2007-5

Language

  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 01050197
  • Record Type: Publication
  • Files: TRIS
  • Created Date: May 24 2007 5:33PM