Combining Property Price Predictions from Repeat Sales and Spatially Enhanced Hedonic Regressions
Hedonic regression and repeat sales are commonly used methods in real estate analysis. While the merits of combining these models when constructing house price indices are well documented, research on the utility of adopting the same approach for residential property valuation has not been conducted to date. Specifically, house value estimates were obtained by combining predictions from repeat sales and various hedonic regression specifications, which were enhanced to account for spatial effects. Three of these enhancements—regression kriging, mixed regressive-spatial autoregressive, and geographically weighted regression—are widely utilized spatial econometric models. However, a fourth augmentation, which addresses systematic residual patterns in regressions with district indicator variables and the presence of outliers in housing data, was also proposed. The resulting models were applied to a dataset containing 16,417 real estate transactions in Oslo, Norway, revealing that when the repeat sales approach is included, it reduces the median absolute percentage error of solely hedonic models by 6.8–9.5%, where greater improvements are associated with less accurate spatial enhancements. These improvements can be attributed to the inclusion of both spatial and non-spatial information inherent in previous sales prices. While the former has limited utility for well-specified spatial models, the non-spatial information that is implicit in previous sales prices likely captures otherwise difficult to observe phenomena, potentially making its contribution highly valuable in automated valuation models.
KeywordsHouse prices Automatic valuation models Spatial models Repeated sales Hedonic regressions Big data
- Amundsen, B. (2015). Rike og fattige flytter fra hverandre i Oslo [Rich and poor moving apart from each other in Oslo]. Forskning.no, Available at: https://forskning.no/samfunnsgeografi/2015/06/rike-og-fattige-flytter-fra-hverandre-i-oslo (accessed: 11 December 2017).
- Anon. (2013). OECD, Eurostat, International Labour Organization, International Monetary Fund, The World Bank, and United Nations Economic Commission for Europe. Repeat sales methods. Handbook on Residential Property Prices Indices (RPPIs), OECD publishing, Paris, 67–72.Google Scholar
- Bohling, G. (2005). Kriging. Data Analysis in Engineering and Natural Science, Kansas Geological Survey. Available at: http://people.ku.edu/~gbohling/cpe940/Kriging.pdf (accessed: 8 June 2018).
- Corcoran, C., & Liu, F. (2014). Accuracy of Zillow’s home value estimates. Real Estate Issues, 39(1), 45–49.Google Scholar
- Eurostat. (2016). Distribution of population by tenure status, type of household and income group − EU-SILC survey. Available at: http://appsso.eurostat.ec.europa.eu/nui/show.do?datasetÆilc_lvho02&langÆen (accessed: 20 May 2018).
- Farber, S., & Yeates, M. (2006). A comparison of localized regression models in a hedonic house price context. Canadian Journal of Regional Science, 29(3), 405–420.Google Scholar
- Fotheringham, A. S., Brunsdon, C., & Charlton, M. (2002). Geographically weighted regression: The analysis of spatially varying relationships. New York: Wiley.Google Scholar
- FreddieMac. (2017). Home Value Explorer. Available at: http://www.freddiemac.com/hve/hve.html (accessed: 5 December 2017).
- Gelfand, A. E., Ghosh, S. K., Knight, J. R., & Sirmans, C. F. (1998). Spatio-temporal modeling of residential sales data. Journal of Business & Economic Statistics, 16(3), 312–321.Google Scholar
- de Haan, J. & E. Diewert (2013), "Hedonic Regression Methods”. Handbook on Residential Property Price Indices, OECD Publishing, Paris, https://doi.org/10.1787/9789264197183-7-en.
- Hengl, T., Heuvelink, G. B. M., & Stein, A. (2003). Comparison of kriging with external drift and regression kriging. Technical note, ITC. Available at: https://webapps.itc.utwente.nl/librarywww/papers_2003/misca/hengl_comparison.pdf (accessed: 11 May 2018).
- Humberset, K. (2018). Her må du punge ut 85.000 kroner for én kvadratmeter [Here you have to pay 85,000 NOK for one square meter]. aftenposten.no. Available at: https://www.aftenposten.no/bolig/Her-ma-du-punge-ut-85000-kroner-for-n-kvadratmeter-10982b.html (accessed: 4 June 2018).
- Monsrud, I. J. & Takle, M. (2018). Price index for existing dwellings. Statistics Norway. Available at: https://www.ssb.no/en/priser-og-prisindekser/statistikker/bpi (accessed: 7 June 2018).
- Eiendom Norge, Eiendomsverdi & FINN.no. (2017). Eiendom Norges boligprisstatistikk [Real Estate Norway housing price statistics]. Available at: http://eiendomnorge.no/wpcontent/uploads/2017/11/Boligstatistikk_oktober_01.pdf (accessed: 4 December 2017).
- Oslo Kommune. (2018). Finn bydelen din her [Find your city district here]. Available at: https://www.oslo.kommune.no/politikk-og-administrasjon/bydeler/bydelsvelger/ (accessed: 13 May 2018).
- Sinnott, R. W. (1984). Virtues of the haversine. Sky and Telescope, 68(2), 159.Google Scholar
- Trawiński, B., Lasota, T., Kempa, O., Telec, Z., & Kutrzyński, M. (2017). Comparison of ensemble learning models with expert algorithms designed for a property valuation system. In N. Nguyen, G. Papadopoulos, P. Jędrzejowicz, B. Trawiński, & G. Vossen (Eds.), Computational collective intelligence , ICCCI 2017, lecture notes in computer science, vol 10448. Cham: Springer.Google Scholar