The focus of this article is the premise that the basic factors that differentiate the market value can include time, place, technical and legal conditions, and buyers and sellers who make decisions based on their preferences and their knowledge of real estate market conditions. As a result, in real estate market analysis, there are certain influences of quantities that cannot be expressed by a functional relationship (e.g., location). In addition, there are a large number of influencing factors and their interaction on the purchase price that are not known or cannot be deduced (e.g., preferences of the purchaser). Extending the regression equation by a signal component in least squares collocation enables the additional information from these value-affecting influences to be exploited. In this way, the extended approach is able to provide a closer representation of real purchase prices.
Property tax administration, Multiple regression analysis
This article is based on a paper presented at the International Workshop on Mass Appraisal Systems held by the FIG (Federation Internationale des Geometres) Commission 9 in Paphos, Cyprus, September 14-16, 2012.
Zaddach, S., & Alkhatib, H. (2014). Least squares collocation as an enhancement to multiple regression analysis in mass appraisal applications. Journal of Property Tax Assessment & Administration, 11(1), 47-66. Retrieved from https://researchexchange.iaao.org/jptaa/vol11/iss1/3