Discrete logit modelling based on state preference data of the analytic hierarchy process for parking choice

The analytic hierarchy process (AHP) is a powerful and qualitative method, that can be considered a means of collecting stated preference (SP) data. But, when it comes to its application to a discrete analysis of travel behaviour or attitudes, the AHP has some methodological limitations. This chapter proposes a modelling framework to develop discrete choice models for a group by using SP data of the AHP. The model is applied to parking choice preferences in the central area of Nagaoka in Japan. We find that absolute measurement is a consistent and flexible method to apply the AHP to the analysis of travel behaviour and preferences.; and nonlinear relationships can be specified between the grades of AHP and physical attributes. To estimate the discrete legit model with better statistical indicators,:we recommend employing the alternatives ranking process, where the choice set of alternatives includes a few alternatives of higher rank. The estimated discrete legit model for parking consists of two parts with good statistical reliability: the capacity of parking places by using revealed preference (RP) data, and other factors such as convenience, facility and economy by using SP data of the AHP. In comparison with the discrete choice model using RP data only, the model using the AHP and RP data can include plural and intangible factors.