Showing results 1 to 2 of approximately 2.(refine search)
Local Polynomial Regressions versus OLS for Generating Location Value Estimates: Which is More Efficient in Out-of-Sample Forecasts?
As an alternative to ordinary least squares (OLS), we estimate location values for single family houses using a standard housing price and characteristics dataset by local polynomial regressions (LPR), a semi-parametric procedure. We also compare the LPR and OLS models in the Denver metropolitan area in the years 2003, 2006 and 2010 with out-of-sample forecasting. We determine that the LPR model is more efficient than OLS at predicting location values in counties with greater densities of sales. Also, LPR outperforms OLS in 2010 for all 5 counties in our dataset. Our findings suggest that LPR ...
Semi-Parametric Interpolations of Residential Location Values: Using Housing Price Data to Generate Balanced Panels
We estimate location values for single family houses by local polynomial regressions (LPR), a semi-parametric procedure, using a standard housing price and characteristics dataset. As a logical extension of the LPR method, we interpolate land values for every property in every year and validate the accuracy of the interpolated estimates with an out-of-sample forecasting approach using Denver sales during 2003 through 2010. We also compare the LPR and OLS models out-of-sample and determine that the LPR model is more efficient at predicting location values. In a balanced panel application, we ...