The impact of space on the application of discrete choice models

In spatial analysis, the 1980s could be characterized as the decade of discrete choice modeling and, more generally, categorized data analysis. Subsequent to the pioneering work undertaken in economics, marketing and transportation, it was quickly recognized that most spatial decisions are discrete and the discrete choice framework was adopted enthusiastically. One of the most popular statistical models for the analysis of discrete choices has been the multinomial logit model (MNL). Space, however, provides a much more complex background against which to model discrete choice than do the aspatial contexts in which the discrete choice modeling (DMC) framework was developed. In this paper we describe the added complexities space introduces into DMC and then discuss how they can be incorporated into the framework to produce more realistic spatial choice models. Our discussion is centered around the MNL model, because of its popularity, and on the role of the Independence from Irrelevant Alternatives (IIA) assumption which is shown to be a key factor in highlighting the differences between aspatial and spatial choice. The first section outlines the implications of IIA for modeling discrete choice processes with particular reference to the MNL. The next section focuses on the reliability of these assumptions in a spatial context. Attention then turns to two alternative paths for relaxing the IIA assumption through explicitly modeling alternative substitutability within the systematic component of utility or implicitly modeling alternative substitutability through the error structure. -from Authors