Examination of the effects of non-measurable explanatory variables on the value of real estate in the process of mass valuation of land

The paper proposes a solution to the problem of how to introduce non-measurable features (attributes) of a property that significantly affect its value to the process of its valuation. The authors adopt two measures enabling them to study the influence of order features on the value of property, the Spearman rank coefficients and standardized βk coefficients, and proceed to check their efficiency, applying an algorithm of mass property valuation (SAMWN) to the sample of 567 plots of land in Szczecin designated for housing purposes. The results thus obtained are then compared with the valuations of these plots of land performed by property appraisers. The study demonstrates that lower valuation errors are obtained when using standardized βk coefficients than the Spearman rank coefficients.