Value of travel time estimation using hierarchical Bayesian mixed logit approach

This paper investigates the value of travel time (VOTT) of commuters traveling on toll facilities of the Port Authority of New York and New Jersey (PANYNJ) and the New Jersey Turnpike (NJTPK) in a time-of-day pricing system. The methodology proposed to estimate VOTT develops hierarchical Bayesian mixed logit models using travel surveys conducted as part of evaluation studies of PANYNJ and NJTPK facilities. The proposed approach is a novel method for examining commuters' behavior on the basis of flexible model specifications. Empirical results show that travel time, toll, income, and departure time are statistically significant parameters affecting VOTT of commuters on PANYNJ toll facilities. Mean VOTT estimates are found to be about $16.5/h for PANYNJ E-ZPass peak users and about $15.15/h for PANYNJ E-ZPass off-peak users, with standard deviation estimates close to $6.45/h during peak periods and $5.72/h during off-peak hours. Similarly, mean VOTT estimates are found to be around $16.3/h for NJTPK E-ZPass peak users and about $14.79/h for NJTPK E-ZPass off-peak users, with standard deviation estimates close to $5.48/h during peak periods and $4.56/h during off-peak hours.