1 A Bivariate Multinomial Probit Model for Trip Scheduling : Bayesian Analysis of

36 37 As tour-based methods for activity and travel participation patterns replaces trip-based methods, time-38 of-day (TOD) choice modeling remains problematic. In practice, most travel demand model systems 39 handle tour scheduling via joint-choice multinomial logit (MNL) models, which suffer from the well-40 known independence of irrelevant alternatives (IIA) assumption. This paper introduces a random utility 41 maximization (RUM) model of tour scheduling called the bivariate multinomial probit (BVMNP). This 42 specification enables correlations across TOD alternatives, both outbound and return (on a tour) and 43 over time slots (in a day). The model is estimated in a Bayesian setting on work-tour data from the San 44 Francisco Bay Area (with 28 time slots). Empirical results suggest that a variety of individual, household, 45 and tour characteristics have reasonable effects on scheduling behavior. For instance, older persons 46 typically pursue work tours at earlier times of day, part-time workers pursue their work tours later, and 47 those with additional activities and tours tend to arrive slightly later and leave much earlier than those