Route and mode choice models using GPS data

Abstract

GPS data has become almost ubiquitous and data collection and processing technologies have advanced considerably. In transportation research, GPS traces are used, along with other data sources, to construct travel diaries, as they promise higher accuracy of collected data, combined with fewer fatigue effects. In this research, we present such a study, where a sample from Zurich, Switzerland, used GPS devices to monitor their daily trips for a week. A follow-up survey provided complementary information, including sociodemographic characteristics of the participants, as well as a large number of attitudinal parameters. Route choice models were estimated using this data set for car and public transport trips, along with a joint route and mode choice model, which also considered bike and walk stages. To the best of our knowledge, this is the first time that GPS data have been used for the estimation of mode and route choice models. The model fit is reasonable for all models and in line with those obtained with traditional data-collection methods. The coefficient estimates have the appropriate signs and meaningful magnitudes. A number of transformations were performed on some of the variables, improving the model fit significantly, and reducing the number of variables. We discuss some of the difficulties associated with such data collection efforts, and point out the advantages that can come from follow-up studies, based on similar concepts.