Modelling sequential choice processes: the case of two-stop trip chaining

Traditional decompositional preferences and choice studies are focused on the prediction of single choices, such as choice of shopping centre or transport mode. Discrete choice experiments are used to derive choice models that predict the probability of choosing a choice alternative as a function of its attributes. In this paper these traditional models are extended by addressing the problem of sequential choice behaviour. It is demonstrated how discrete choice experiments and universal logit models may be used to predict a choice sequence. The approach is illustrated for the problem of trip chaining. The research findings support the suggested approach.