Teoretyczne i praktyczne aspekty opisu cech jakościowych nieruchomości w modelach regresji wielorakiej wyceny wartości mieszkań

The increasing number of transactions and areas of economic activity requiring the value of real estate to be determined have prompted attempts to implement multiple regression models to increase as well. However, the imperfections of regression modeling, and property as real objects described in the models, lead to contradictory and unjustified conclusions. One of the reasons for the functional imperfections of regression models is the method employed for inputting qualitative variables. Unfortunately, these variables are most commonly used in the decryption of property characteristics. According to the principles defining possible operations on numbers depending on the type of measurement scale used (nominal and ordinal), the qualitative variables can be introduced into regression models as dummy variables. In this article, we propose an alternative method for implementing qualitative variables (describing the real estate markets) in multiple regression models, by applying Osgood scale to measure them. This paper presents not only a theoretical basis of the proposed model but also the results of empirical data on the classical method of using qualitative variables. The theoretical considerations are supported by an empirical study on the residential housing market in Szczecin, Bydgoszcz and Świecie (zachodniopomorskie voivodeship).