Joint World Congress of International-Fuzzy-Systems-Association (IFSA)/European Conference of European-Society-for-Fuzzy-Logic-and-Technology (EUSFLAT), Lisbon, Portekiz, 20 - 24 Temmuz 2009, ss.351-356
Relationships between geographically referenced variables are usually spatially heterogeneous and, to account for such variations, local models are necessary. This paper compares the Geographically Weighted Regression (GWR) model, usually used to integrate and examine the spatial heterogeneity of a relationship, and the Fuzzy Clustering-Based Least Squares (FCBLS) model for the analysis of spatially varying relationships. Both models use the same model parameters and bandwidth values derived from the Akaike Information Criterion. The results show that FCBLS outperforms the GWR model.