The Problem of Ensuring Representative Samples when Modeling the Market Value in the Regional Real Estate Market

The article describes the problem of the lack of a universal adequate method for achieving the representativeness of a sample of real estate objects when modeling their market value.

The purpose of the work is to develop a methodology for creating a representative sample of real estate objects. This method can be used by specialists when working with inactive real estate markets in small cities and settlements. On the example of the market of land plots for individual housing in several cities of the Krasnodar krai, the analysis of the features of ensuring representativeness is carried out. There are opportunities and limitations of various tools for forming a representative sample.

Materials and methods. When preparing the paper, the author studied the experience of forming representative samples accumulated by Russian and foreign scientists, considered in detail theoretical and practical approaches to analyzing the quality of the general set of market real estate objects. The methodology proposed in the article was tested on the example of the real estate market of the cities of Krasnodar, Goryachy Klyuch, Armavir. Тhe author used cartographic data, information from specialized portals of the real estate market and from the unified state register of rights. To achieve the objective, theoretical methods (comparative analysis, synthesis, generalization, analogy) and modelling were used.

The main result of the paper is a reasonable method of radial circles, which allows you to select high-quality objects in a sample. Such land plots according to a certain significant price-forming factor in the city under consideration structurally correspond to the plots registered in the unified state real estate register. It is important to establish the conditions under which the sample becomes representative of the pricing factor associated with the location of the object. Тhe analytical material, stages and methods of selecting units in the sample presented in the article are of interest for the real estate researchers, analysts and experts, practitioners of state budgetary institutions engaged in state cadastral valuation.

Conclusion. The method of radial circles can be further developed and used for other price-forming factors when modeling the market value of real estate.

1. Anisimova I.N., Barinov N.P., Gribovskiy S.V. Accounting for different types of pricing factors in multidimensional models of real estate appraisal. Voprosy otsenki = Evaluation Issues. 2004; 2: 2-15. (In Russ.)

2. Sanina L.V., Sherstyankina N.P., Bergen D.N., Dashkevich P.M. Modeling the cost of apartments in the regional residential real estate market (on the example of the Irkutsk region). Izvestiya vuzov. Investitsii. Stroitel’stvo. Nedvizhimost’ = Proceedings of universities. Investments. Construction. Real estate. 2017; 7; 3(22): 27-41. DOI: 10.21285/2227-2917-2017-3-27-41. (In Russ.)

3. Fallis G. Housing Economics. Toronto: Butterwort; 1985. 250 p.

4. Basu S., Thibodeau T. G. Analysis of Spatial Autocorrelation in House Prices. Journal of Real Estate Finance and Economics. 1998; 17: 61-85.

5. Isaac F. Megbolugbe Econometric Analysis of Housing Trait Prices in a Third World City. The Journal of Regional Science. 1986; 26; 3: 533-547.

6. Yarushkina N.A. Modeling the dynamics of the real estate market. Zhilishchnoye stroitel’stvo = Housing construction. 2006; 12: 5-6. (In Russ.)

7. Sternik S.G. Methodology of discrete spatial-parametric modeling of real estate markets. Prikladnaya matematika i voprosy upravleniya = Applied Mathematics and Management Issues. 2020; 4: 155-185. DOI 10.15593/2499-9873/2020.4.10. (In Russ.)

8. Sidorenko O.A. The main directions of economic and mathematical modeling of the residential real estate market. Ekonomika, statistika i informatika. Vestnik UMO = Economics, statistics and informatics. Bulletin of UMO. 2013; 3: 153-158(In Russ.)

9. Robert C. MacCallum, Keith F. Widaman, Kristopher J. Preacher, Sehee Hong Sample Size in Factor Analysis: The Role of Model Error. Multivariate Behavioral Research. 2001; 36; 4: 611637. DOI: 10.1207/S15327906MBR3604_06.

10. Agalakov S.A. Econometric modeling of the cadastral value of land plots in the Omsk region. Vestnik Omskogo universiteta = Bulletin of Omsk University. 2015; 1(75): 13-15. (In Russ.)

11. Berdnikova V.N., Osennyaya A.V., Khakhuk B.A. Construction of a qualitative model for assessing the cadastral value of real estate. Ekonomika i matematicheskiye metody = Economics and Mathematical Methods. 2021; 57; 2: 73-84. DOI 10.31857/S042473880014895-3. (In Russ.)

12. Gladkikh N.I., Kuznetsova V.V. Determination of the required number of analogs for a given number of pricing factors for the purpose of real estate appraisal using the methods of correlation-regression analysis. Imushchestvennyye otnosheniya v RF = Property relations in the Russian Federation. 2016; 6(177): 75-84. (In Russ.)

13. Prikaz Minekonomrazvitiya Rossii ot 12.05.2017 № 226 «Ob utverzhdenii metodicheskikh ukazaniy o gosudarstvennoy kadastrovoy otsenke» = Order of the Ministry of Economic Development of Russia dated 12.05.2017 No. 226 «On approval of guidelines on state cadastral valuation». (In Russ.)

14. Adler YU.P. Is your sample representative? Kontrol’ kachestva produktsii = Product quality control. 2016; 5: 39-43. (In Russ.)

15. Dmitriyev YA. V. Determination of the error of representativeness and required sample sizes when calculating the values of the main indicators of correlation, variance and regression analysis using the Chebyshev formula. Vestnik Moskovskogo gosudarstvennogo universiteta priborostroyeniya i informatiki. Seriya: Priborostroyeniye i informatsionnyye tekhnologii = Bulletin of the Moscow State University of Instrument Engineering and Informatics. Series: Instrument making and information technology. 2014; 53: 94-100. (In Russ.)

16. Iskra V.V., Iskra N.A., Tatur M.M. Influence of statistical characteristics of the training sample on its representativeness. Iskusstvennyy intellect = Artificial Intelligence. 2013; 4: 325-332. (In Russ.)

17. Gribovskiy S.V., Barinov N.P. Assessment of real estate for taxation. Imushchestvennyye otnosheniya v RF = Property relations in the Russian Federation. 2006; 5(56): 96-106. (In Russ.)

18. Smirnov R.M., Garina I.O. Statistical methods of data analysis. Molodezhnyy nauchnotekhnicheskiy vestnik = Youth Scientific and Technical Bulletin. 2015; 2: 11. (In Russ.)

19. Shabalina O. N. Peculiarities of recognizing the market as active or inactive. Classification of markets by the level of activity. Imushchestvennyye otnosheniya v Rossiyskoy Federatsii = Property relations in the Russian Federation. 2018; 11(206): 65-82. (In Russ.)

20. Bedin B.M. Koshman V.N., Khomkalov G.V. Massovaya otsenka rynochnoy stoimosti zhiloy nedvizhimosti v mnogofunktsional’nom gorode: teoriya i praktika = Mass appraisal of the market value of residential real estate in a multifunctional city: theory and practice. Irkutsk: BSUEP; 2006. 123 p. (In Russ.)

21. Shtorm R. Teoriya veroyatnostey. Matematicheskaya statistika. Statisticheskiy kontrol’ kachestva = Probability theory. Math statistics. Statistical quality control. Moscow: Mir; 1970. 368 p. (In Russ.)

22. Taushanov Z., Toneva Ye., Penova R. Calculation of the entropy coefficient for small samples. Izobretatel’stvo, standartizatsiya i kachestvo= Invention, standardization and quality. 1973; 5: 48-52. (In Russ.)

23. Kartograficheskiye dannyye Yandeks.Karty = Map data Yandex.Maps [Internet]. Available from: https://yandex.ru/maps/?ll=39.782117%2C45.0290 56&z=9.2. (In Russ.)

24. Spetsializirovannyye internet-portaly po rynkam nedvizhimosti = Specialized Internet portals for real estate markets [Internet]. Available from: https://www.avito.ru, https://ruads.org. (In Russ.)

25. Spravochnaya informatsiya ob ob»yektakh nedvizhimosti v rezhime online = Reference information about real estate objects online [Internet]. Available from: https://rosreestr.gov.ru/wps/portal/online_request. (In Russ.)