Spatial heterogeneity and the geographic distribution of airport noise
Abstract: One might expect that houses closer to an airport and those in higher minority population neighborhoods experience more airport noise. We find evidence supporting these conjectures when estimating a standard ordered probit model for houses sold near the Atlanta airport. However, because the various neighborhood demographics surrounding the airport can be heterogeneous, and the noise contours are not necessarily correlated with distance in certain neighborhoods, we hypothesize that the impacts of explanatory variables on the probability of greater noise vary across space. We explore spatial heterogeneity by estimating ordered probit locally weighted regressions (OPLWR). These results differ from those using a standard ordered probit model. Moreover, we find notable differences in parameter estimates for different observations (i.e., houses). Even in relatively small areas, our results imply that the standard ordered probit model can generate biased estimates.
File(s): File format is application/pdf http://research.stlouisfed.org/wp/2009/2009-058.pdf
Provider: Federal Reserve Bank of St. Louis
Part of Series: Working Papers
Publication Date: 2009