An Empirical Evaluation of the Aggregated Spatial Choice Model

Abstract

The purpose of this paper is to demonstrate the performance and capabilities of the aggregated spatial choice model with empirical data. The application is to a problem of Canadian interregional migration in the 1990-91 time period. The strength of the aggregated model is its ability to capture the role of elemental processes in defining the attractiveness of aggregate spatial units without knowledge of elemental choices. The theory of the aggregated model has been discussed in the discrete choice literature. Applications of the model, however, have been very limited in number, while the model in its complete form has never been applied. The application intends to demonstrate the use of the model in the spatial context. The idea that the spatial resolutions of attribute and choice data do not need to be identical can address the aggregation difficulties often inherent in spatial choice problems.