MCMC Bayesian spatial filtering for hedonic models in real estate markets

Abstract

The traditional hedonic model postulates that housing prices depend on their characteristics and their location. However, this model assumes a constant relationship between the dependent and the independent variables. This assumption is unrealistic because empirical studies have shown that the regression coefficients depend on the housing location. For this reason, it is necessary to use models with spatially varying coefficients. The approaches proposed in the literature used to estimate this type of models do not incorporate the uncertainty associated with the estimation and selection of models and/or are computationally expensive. To improve these aspects, this paper proposes spatial filtering techniques to parsimoniously model the spatial dependencies of the hedonic coefficients and an adaptive MCMC algorithm of Bayesian variable selection to select the most appropriate filters. The method is illustrated through an application to the real estate market of Zaragoza, and a comparison with alternative procedures is conducted. Our results show that our valuation methodology has better goodness of fit and predictive performance properties than alternative methods. Although our proposal assumes normality and homoscedasticity of the model error distribution, the method is easy to implement and not very computationally demanding, which makes this approach attractive and useful from a practical viewpoint.

The impact of neighborhood services on land values: an estimation through the hedonic pricing model

“…In housing and property prices estimation the hedonic model is used for the valuation of locational factors which use the regression technique for numerical estimation of data (Selim 2009). Some methods used the locational postulates only for prices estimation (Gargallo et al 2017), But this study assumed the constant relationship among dependent and independent variables. Below, concept diagram provide overall process adopted to complete the research plan (Fig.…”

The Probabilistic Genotyping Software STRmix: Utility and Evidence for its Validity

“…MCMC is a widely used technique and is considered a mainstream statistical tool. It is used in real estate market prediction (41), earthquake and rock fracturing (42), electricity capacity modeling (43), weather prediction (44), betting (45), climate (46), computational biology (47), computational linguistics (48), genetics (49), engineering (50), physics (51), aeronautics (52), stock market prediction (53), and social science (54). The key papers describing the algorithms used within the MCMC are Metropolis et al (55), with 37,506 cites in Google Scholar (as at May 27, 2018), and Hastings (56), with 12,229 cites providing some measure of their widespread acceptance and use.…”

Analysis of different approaches to real estate appraisal

“…Therefore, the noncritical use of spatial econometrics may cause problems in the interpretation of individual parameters. Another possible solution would be to weaken multicollinearity by constructing Bayesian models that use variable coefficient processes to model non-constant linear relationships between variables (Gargallo, Miguel, & Salvador, 2017). According to (Yeh & Hsu, 2018) the traditional statistical method, basically, the type and measure of the variable define the most suitable model for use.…”

“…According to (Yeh & Hsu, 2018) the traditional statistical method, basically, the type and measure of the variable define the most suitable model for use. The traditional valuation model is based on the hedonic model to estimate housing prices (Gargallo, Miguel, & Salvador, 2017).…”

“…Finally, a decision tree based on algorithms and preliminary definition of the best rules (Tobergte & Curtis, 2013) was created. The hedonic model was used in this research to estimate housing prices, since this method is considered the most used (Gargallo, Miguel, & Salvador, 2017) and incorporated in the international standards of evaluation (IVS) and in the European evaluation standards (EVS) as an approach that estimates a market value. This method has been criticized due to the problems of multicollinearity in the estimation of the parameters, which are due to the very similar characteristics of the houses in the same area, which makes it difficult to estimate the regression coefficients (Bárcena et al, 2014).…”