Does the choice model method and/or the data matter?
The opportunity to have seven data sets associated with a stated choice experiment that are very similar in content and design is rare, and provides an opportunity to look in detail at the empirical evidence within and between each data set in the context of a range of discrete choice estimation methods, from multinomial logit to latent class to scale multinomial logit to mixed logit, and the most general model, generalized mixed multinomial logit that accounts for preference and scale heterogeneity. Given the problems associated with data from different countries and time periods, we estimate separate models for each data set, obtaining values of travel time savings that are then updated post estimation to a common dollar for comparative purposes. We also pooled all data sets for a scaled MNL model, treating each data set as a set of three separate utility expressions, but linked to the other data sets through scale heterogeneity. This is not behaviourally appropriate with MNL, latent class or mixed logit. The main question investigated is whether there exists greater synergy in the willingness to pay evidence within model form across data sets compared to across model forms within data sets. The evidence suggests that there is a relatively greater convergence of evidence across the choice models, with the exception of generalized mixed logit, after controlling for data set differences; and there is strong evidence to suggest that differences between data sets do matter.
Identifying commuter preferences for existing modes and a proposed metro
In 2009, the New South Wales government announced that it would be proceeding with a feasibility study to identify the patronage potential of a new Metro rail system for Sydney. As part of this study, a new modal choice study was undertaken to establish the role of traditional attributes such as travel times and costs (and more recently, reliability) but also somewhat neglected influences such as crowding, where the later has a critical role in the calculation of capacity needs at railway stations. This paper focuses on the commuter segment and develops a new stated choice experiment in which travellers are able to compare the proposed new Metro with existing available modal alternatives for access, linehaul and egress trip stages, with a particular emphasis on the incorporation of crowding represented by the availability of a seat vs. standing in existing and new public transport modes. We present the error component choice model together with estimates of mode-specific willingness to pay for travel time components, service frequency and crowding, that latter expressed in terms of the probability of getting a seat and the probability of avoiding standing.
