Assessing the Impact of Selected Attributes on Dwelling Prices Using Ordinary Least Squares Regression and Geographically Weighted Regression: A Case Study in Poznań, Poland

Abstract

The price of dwellings is determined by a number of attributes among which location factors are usually the most important. Comprehensive analyses of the real estate market should take into account a broad spectrum of attributes including economic factors, physical, neighborhood and environment characteristics. The primary objective of the study was to answer the question of what determinants affect transaction prices within the housing market in Poznań. The analysis was performed on the basis of source data obtained from the Board of Geodesy and Urban Cadastre GEOPOZ in Poznań. In our study, we used two research regression methods: ordinary least squares and geographically weighted regression. The estimated models made it possible to formulate specific conclusions related to the identification of local determinants of housing prices in the Poznań housing market. The results of the study confirmed that the use of the proposed techniques makes it possible to identify attributes relevant to the local market, and, moreover, the use of spatial analysis leads to an increase in the quality of the description of the characteristics of the analyzed phenomenon. Finally, the results obtained indicate the diversity of the analyzed market and highlight its ambiguity and complexity.