To cut down car trips in rush hours, a social P&BR (Park and Bus Ride) experiment has been adopted in Kofu, Japan. During the experiment days, a set of Stated Preference (SP) data and Experiment Day (ED) data are obtained. SP data is frequently used to estimate a model of traffic demand. However, it is considered that there are some biases in SP data, and it works on the results estimated. In this paper, we propose a combined model with ED data and SP data for decreasing the effect of biases. The result of a case study and a sensitivity analysis indicates that the combined model has higher precision than a SP model, and is stable against the change of explanatory variables.
No takes yet. Share an insight, caveat, or question.
Guan et al. (2000) studied this question.
Synapse has enriched one closely related paper. Consider it for comparative context: