Analysing the relationship between residential property prices and their determinants: a semiparametric geographically weighted regression approach

This paper analyses the relationship between residential property prices and their determinants, taking account of the local geography. A semiparametric geographically weighted regression (S-GWR) technique is employed to explore this relationship. Selling prices, structural and locational attributes data were collected from the database of the. The Department of Valuation and Services of Malaysia, including selected maps and reports. The outcome of this paper shows a strong geographically varying relationship between residential property prices and their determinants in which the residential property price determinants have a positive impact on prices in some areas but a negative or no impact on others. The magnitude of the effect is also found to be geographically varied; the capitalisation in residential property prices is found to be greater in some areas but less or nil in other parts. The use of S-GWR technique allows such geographically varying relationships to be exposed, hence leading to a better understanding of the relationship between residential property prices and their determinants.