Continuous Departure Time Models A Bayesian Approach

Models of departure time presently rely on discrete choice or simple proportions across blocks of time within a 24-h day. Duration models allow for more flexible specifications to explain both unimodal (one-peak) and multimodal (multipeak) data, which are common in (aggregate) departure time data. This paper offers Bayesian estimates of continuous departure time models using accelerated failure time specifications for various trip purposes with several distributional specifications, including the log-normal, Weibull, Weibull with and without unobserved heterogeneity, and a mixture of normals. The home-based work and non-home-based trip models are created by means of unimodal distributions; the home-based nonwork trip departure times are modeled via a bimodal distribution. The results indicate that a Weibull with unobserved heterogeneity performs well among unimodal distributions, and that the multipeak profile can be modeled well with a mixture of normals.