The daily activity schedule model for transportation demand analysis: Modifications and applications
Abstract
The purpose of this research was to address the shortcomings of the daily activity schedule model and introduce changes in the model system in order to more fully utilize the potential benefits of such a system. The major problem with the previously developed model was its full reliance on the sequential procedure to estimate the system of nested logit models. Such a procedure can cause the coefficient estimates of the models not to be asymptotically efficient. In addition, the estimation procedure overestimates the t-statistics of these coefficients, thereby giving the illusion that some of these variables might be significant and important, when in reality they are not. The model also encounters other problems when data used in the estimation process is not collected in a purely random manner. This research has also used the improved model system in order to investigate what might happen in the event there are changes in the transportation system. Imposing a congestion tax during peak hour periods of the day, as well as imposing parking fees, were investigated to see how might such changes affect the mode choice of the population, as well as the various types of households in the data sample.
Degree
Ph.D.
Advisors
Fricker, Purdue University.
Subject Area
Civil engineering|Systems science|Transportation
Off-Campus Purdue Users:
To access this dissertation, please log in to our
proxy server.