Local Spatial Interaction Modelling Based on the Geographically Weighted Regression Approach

摘要: One of the recent major trends in spatial analysis is local modelling by which analysts examine properties geographical phenomena (Fotheringham, 1997). Indeed, processes tend to vary over space due different contexts so that non-stationarity emerges (Jones III and Hanham, 1995). In such cases, global models postulate universally acceptable fail capture real under study. We could say inferences incidence rates disease mapping are simplest form (Openshaw et al.,1987, Nakaya, 2000). As for more complicated association analyses, Casetti’s (1972) expansion method popular model explicitly property regression (e.g. Casetti, 1990). According method, we can specify drifts parameters polynomial or harmonic series locational variables. Recently, Newcastle school (Brunsdon al., 1996, Fotheringham al.,1998) has developed a generalised methodology, called geographically weighted (GWR). The approach estimates coefficients with moving weighting kernel.