Determinants of New Housing Prices in Bogotá for 2019: an Approach Through a Semiparametric Spatial Regression Model

This document uses the recent advances in the field of spatial econometrics to develop a semi-parametric regression model that allows the inclusion of non-linearities and the modeling of spatial heterogeneity through a two-dimensional function that depends on geographic coordinates. The methodology is applied in a hedonic model for the price of new housing in Bogotá where a remarkable fit is obtained, in terms of the mean square error and the R2. The empirical result shows that the housing delivery condition, stratum, and construction state affect the price in a linear way, while the area, and the distances to parks, roads and Transmilenio stations present non-linear results, additionaly, it was possible to model the spatial trend that represents the location on the value of  the house where an increase is appreciated towards the northeast of the city. Thus, it is concluded that the estimated model allows the relationship between the explanatory variables and the dependent variable to be measured flexibly, establishing itself as a good alternative to understand the formation of prices in the real estate market.

• Autores: Tolaza-Delgado, Jurgen; Melo-Martínez, Oscar; Azcarate-Romero, Juan
• Fecha de publicación: 2021
• Institución: Universidad EAFIT
• Repositorio: Repositorio EAFIT
• Idioma: spa
• OAI Identifier: oai:repository.eafit.edu.co:10784/31018
• Acceso en línea: http://hdl.handle.net/10784/31018
• Palabra clave: Hedonic models; spatial econometrics; housing price; semiparametric regression; Modelos hedónicos; Econometría espacial; Precios de vivienda; regresión semiparamétrica
• License: Copyright © 2021 Jurgen Toloza-Delgado, Oscar Melo-Martínez, Juan Azcarate-Romero