Dynamic Discrete Choice Models for Transportation

Abstract

Discrete choice models have received widespread acceptance in transport research over the past three decades, being used in travel demand modelling and behavioural analysis; however, their applications have been mainly developed in a static context. There have been several dynamic models in transportation; but these formulations are not based on dynamic optimization principles and do not allow for changes in external factors. With the continuous and rapid changes in modern societies (i.e. introduction of advanced technologies, aggressive marketing strategies and innovative policies) it is more and more recognized by researchers in various disciplines from economics to social science that choice situations take place in a dynamic environment and that strong interdependencies exist among decisions made at different points in time. Dynamic discrete choice models (DDCMs) describe the behaviour of a forward-looking economic agent who chooses between several alternatives repeatedly over time. DDCMs are usually specified as an optimal stopping problem, where agents decide when to make a change in ownership of durable goods or in their behaviour. In this paper, we present the application of the dynamic formulation to short- to medium-term vehicle-holding decisions.

Acknowledgements

We would like to thank the three anonymous reviewers whose comments helped to improve an earlier version of this paper.

Notes

In a probabilistic approach, where all available information is contained in the observation, decision rules are in general based on the conditional probability. A common procedure is to define a cost function that is minimized or maximized by the optimal decision rule.

Costs are in general not directly observable, so they are inferred from observations. In Rust case study, a total cost function is estimated with parameter θ ₁.

Consumer outflow from the car market can be handled in duration models. What these models lack is the theoretical background in dynamic optimization.