Accurate estimation of prevailing housing prices is important for both business and research investigation of housing and mortgage markets. Quality-adjusted house price indices have already been constructed using traditional hedonic models. These hedonic models don't incorporate the spatial structure in housing data sets. In this article, we argue that spatial structure is more important in the precision and accuracy of resulting price estimations. The housing sales data we employ have been actually observed in Chengdu housing market in 2010. We examine the spatial relationship using the Global and Local Moran's I statistics of the hedonic residuals. As the data sets show spatial structure, we illustrate the importance of spatial autocorrelation in both the specification and estimation of hedonic models, and then apply the spatial model in estimating zone level price index. We also assess the accuracy of both models, and conclude that considering spatial relationship in the spatial hedonic model is significant, since the spatial hedonic model is more accurate in estimating housing prices. © 2014 Springer-Verlag Berlin Heidelberg.
CITATION STYLE
Xin, L., & Zheng, S. (2014). Spatial analysis and spatial house price index construction: Evidence from chengdu housing market. In Proceedings of the 17th International Symposium on Advancement of Construction Management and Real Estate (pp. 1207–1217). Springer-Verlag Berlin Heidelberg. https://doi.org/10.1007/978-3-642-35548-6_122
Mendeley helps you to discover research relevant for your work.