Evaluating Spatial Model Accuracy in Mass Real Estate Appraisal: A Comparison of Geographically Weighted Regression and the Spatial Lag Model

Paul E. Bidanset
University of Ulster and the City of Norfolk, Virginia

John R. Lombard
Old Dominion University

SpAM
SpAM (Spatial Analysis and Methods) presents short articles on the use of spatial statistical techniques for housing or urban development research. Through this department of Cityscape, the Office of Policy Development and Research introduces readers to the use of emerging spatial data analysis methods or techniques for measuring geographic relationships in research data. Researchers increasingly use these new techniques to enhance their understanding of urban patterns but often do not have access to short demonstration articles for applied guidance. If you have an idea for an article of no more than 3,000 words presenting an applied spatial data analysis method or technique, please send a one-paragraph abstract to rwilson@umbc.edu for review.

Geographically weighted regression (GWR) has been shown to greatly increase the performance of ordinary least squares-based appraisal models, specifically regarding industry standard measurements of equity, namely the price-related differential and the coefficient of dispersion (COD; Borst and McCluskey, 2008; Lockwood and Rossini, 2011; McCluskey et al., 2013; Moore, 2009; Moore and Myers, 2010). Additional spatial regression models, such as spatial lag models (SLMs), have shown to improve multiple regression real estate models that suffer from spatial heterogeneity (Wilhelmsson, 2002). This research is performed using arms-length residential sales from 2010 to 2012 in Norfolk, Virginia, and compares the performance of GWR and SLM by extrapolating each model’s performance to aggregate and subaggregate levels. Findings indicate that GWR achieves a lower COD than SLM.