Spatial Patterns of the Housing Market: Multi-Dimensional Non-Euclidean Notion of Space

Abstract

This paper highlights three key aspects of the quantitative analysis of space in the housing market: i) spatial heterogeneity ii) spatial interaction, and iii) spatial scale. The difficulties of identifying housing markets and understanding the levels of interaction established between sub-markets is widely stressed in the literature, as well as a range of appropriate methods to analyze them. However, there is no consensus on the methodologies to be applied. In order to contribute to the understanding of the spatial structure of housing market, with special emphasis on spatial dependence, we present a methodology and results of their empirical application. Contrary to the traditional approach that considers an a priori definition of spatial weight matrix (W), we present a non parametric approach that allows estimating W.