New Study by Center for Economic Education Provides Guidance on Econometrics Issues in Real Estate Research

Hedonic regression models of house prices increasingly incorporate information about location into both the non-stochastic (the regression model) and stochastic (error structure) components of the empirical model. These models typically incorporate information about location into the non-stochastic portion of regression models in one of two ways: either by including a set of dummy variables to represent individual locations called “neighborhoods,” or by using a set of distance (or travel time) variables to characterize house locations in terms of proximity to amenities and dis-amenities. Recent research presents an alternative to the second of these approaches that instead uses a latitude-longitude co-ordinate system that requires no information on the number of amenities (dis-amenities) or their locations. One virtue of this alternative claimed by its authors is that it can eliminate omitted variables bias in the estimation of the coefficients of non-distance variables in the case where the locations of the amenities are unknown or incorrect.

     A new study by Turner College economist Frank Mixon, Director of the Center for Economic Education, and his colleagues Steven Caudill and Neela Manage, both of Florida Atlantic University, conducts a very extensive set of Monte Carlo simulations in order to examine claims made about the use of a co-ordinate system. The Mixon et al. study, which appears in the latest issue of Real Estate, shows that many of the claims made in this research, particularly those referencing the elimination or diminution of “biases of coefficients of non-distance variables,” are, given the particulars of the Monte Carlo experiments, not possible to investigate. Mixon et al. further show that there is no omitted variables bias present because the non-distance variable is uncorrelated with any of the other variables used in regression models.  This is the second study published in about as many years by Mixon and Caudill that provides guidance on econometrics issues in real estate research. The two authored a 2022 article in the Journal of Econometric Methods showing how marginal effects for time on the market and probability of sale can be obtained from any hazard model, and extending the generalization of the geometric hazard model to include covariates for use in the estimation of time on the market and probability of sale regressions in real estate, thus creating an entirely new hazard model based on probability of sale rather than time on the market.