Abstract
GIS-based multicriteria analysis is a procedure for combining a set of criterion maps and
associated criterion weights to obtain an overall value for each spatial unit (location) in the
study area. Ordered Weighted Averaging (OWA) is a generic algorithm of multicriteria
analysis. It has been integrated into GIS and applied for tackling a wide range of spatial
problems. However, the conventional OWA method is based on an assumption of spatial
homogeneity of its parameters. Therefore, it is referred to as a global model. This thesis
proposes a local form of OWA. The local model is based on the range sensitivity principle. A
case study of examining spatial patterns of socioeconomic status in London, Ontario is
presented. The results show that there are substantial differences between the spatial
patterns generated by the global and local OWA methods.