CONTEXTUAL MODELS OF URBAN HOUSE PRICES - A COMPARISON OF FIXED-COEFFICIENT AND RANDOM-COEFFICIENT MODELS DEVELOPED BY EXPANSION

Contextual quantitative models are receiving considerable attention in the geographic literature in the form of models developed by the ''ex pansion method.'' The majority of these models have involved the expan sion of the fixed part of the model and are in many cases equivalent t o standard ANOVA and ANCOVA procedures. Models from a ''multilevel per spective,'' in which the expansion takes place in the random part of t he model, have also been developed. Although these two methods converg e conceptually, major differences in the form of the models can be spe cified and estimated. This paper develops contextual models of house p rices using both approaches. We argue that varying-parameter multileve l models, which recognize that houses are nested within districts, are preferable to the usual single-level, fixed-coefficient models. We il lustrate both approaches with data on house prices in London.