Stated response and multiple discrete-continuous choice models: Analyses of residuals

In sophisticated transport models, choice modelling is used to capture a wide range of behaviour, such as mode choice, vehicle choice and route choice. A newly developed approach to improving realism is the multiple discrete-continuous extreme value (MDCEV) model, which allows researchers to model the allocation of continuous amounts of a consumer good. Before implementing this model in overall frameworks, it is important to determine the accuracy of the forecasting. In this paper, an MDCEV model of household fleet choice based on data collected in a stated adaptation survey is presented. The model was used to predict the annual mileage of households with regard to 17 different types of cars, and the results of that forecast were compared to the actual data by calculating the residuals. The residual analysis showed that the model performed significantly better than a completely random model, but the share of wrongly allocated mileage, 70% of the total, remained high. However, the results of only one model were not sufficient to assess the procedure. The differences between two submodels, one with and one without public transport, regarding the distribution of the residuals indicated that model specification has a significant influence on performance. Therefore, more work on forecasting additional MDCEV models was necessary to have a basis for comparison. We compared two further MDCEV models to obtain a fuller understanding of their performance.