The Impact of Space on the Application Of Discrete Choice Models

摘要: In spatial analysis, the 1980's could be characterized as decade of discrete choice modeling and, more generally, categorized data analysis. Subsequent to pioneering work undertaken in economics, marketing and transportation, it was quickly recognized that most decisions are (for example, selection a city which live or store at shop) framework adopted enthusiastically. One popular statistical models for analysis choices has been multinomial logit model (MNL). this paper we describe added complexities space introduces into Discrete Choice Modeling then discuss how they can incorporated produce realistic models. Our discussion is centered around MNL model, because its popularity, on role Independence from Irrelevant Alternatives (IIA) assumption shown key factor highlighting differences between aspatial choice. We also demonstrate certain where IIA relaxed subtleties not captured sufficiently these only by developing theory. Some promising beginnings direction reported.