An individual's responsiveness to level-of-service variablesaffects her or his travel mode choice for a trip. This responsivenesswill, in general, vary across individuals based on observed (to ananalyst) and unobserved (to an analyst) individual characteristics.The current paper formulates a multinomial-logit based model oftravel mode choice that accommodates variations in responsiveness tolevel-of-service measures due to both observed and unobservedindividual characteristics in a comprehensive manner. The choiceprob- abilities in the resulting model are evaluated using MonteCarlo simulation techniques and the model para- meters are estimatedusing a maximum simulated likelihood approach. The model is appliedto examine the impact of improved rail service on weekday, businesstravel in the Toronto-Montreal corridor. The empirical results showthat not accounting adequately for variations in responsivenessacross individuals leads to a statistically inferior data fit andalso to inappropriate evaluations of policy actions aimed atimproving inter-city transportation services.
展开▼