1# RECORD 973124ea687da38bfcb0d526fb28745dae9e1e902# TITLE: MCMC Bayesian spatial filtering for hedonic models in real estate markets3# YEAR: 2017.0 VENUE: nan DOI: 10.1016/j.spasta.2017.07.0104# AUTHORS: P. Gargallo; Jesus Miguel; M. Salvador5# PAGES: 37 CANDIDATE TABLE PAGES (1-based): []6# ABSTRACT: 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 Bayesian algorithm 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.789===== PAGE 1 (score 5, numeric-paren 0, table-words 0, var-words 5) =====10111 12 13MCMC BAYESIAN SPATIAL FILTERING FOR HEDONIC 14MODELS IN REAL ESTATE MARKETS 15Gargallo, P. ; Miguel, J.A. and Salvador, M.J. * 16 17emails: pigarga@unizar,es, jamiguel@unizar.es, salvador@unizar.es 18Departamento of Estructura e Historia Económica y Economía Pública 19Facultad de Economía y Empresa. University of Zaragoza (SPAIN) 20 21Abstract 22The traditional hedonic model postulates that housing prices depend on their 23characteristics and their location. However, this model assumes a constant relationship 24between the dependent and the independent variables. This assumption is unrealistic 25because empirical studies have shown that the regression coefficients depend on the 26housing location. For this reason, it is necessary to use models with spatially varying 27coefficients. The approaches proposed in the literature used to estimate this type of 28models do not incorporate the uncertainty associated with the estimation and selection 29of models and/or are computationally expensive. To improve these aspects, this paper 30proposes spatial filtering techniques to parsimoniously model the spatial dependencies 31of the hedonic coefficients and an adaptive MCMC algorithm of Bayesian variable 32selection to select the most appropriate filters. The method is illustrated through an 33application to the real estate market of Zaragoza, and a comparison with alternative 34procedures is conducted. Our results show that our valuation methodology has better 35goodness of fit and predictive performance properties than alternative methods. 36Although our proposal assumes normality and homoscedasticity of the model error 37distribution, the method is easy to implement and not very computationally demanding, 38which makes this approach attractive and useful from a practical viewpoint. 39 40 41Keywords: Bayesian Inference; Variable Selection; Adaptive MCMC; Hedonic 42Models; Real Estate Market; Spatial Filtering; Geographically Weighted Regression. 43 44* This work was supported by grants ECO2012-35029 and ECO2016-79392-P of the Ministerio 45de Economía y Competitividad (Spain) 46 471. Introduction 48 49Real estate activities are linked to many sectors of the economy, including 50construction, finance, and insurance. Therefore, updated fair market housing values are 51extremely valuable to financial regulators and institutions, municipal assessors, housing 52index compilers, real estate developers, investors, and many others. Hedonic modelling 53is the most widely used method to estimate housing prices. 54The traditional hedonic model postulates that housing prices mainly depend on 55their characteristics and locations. The model accounts for locational attributes (location 56