Abstract
The choice of weights is a non-nested problem in most applied spatial econometric models. Despite numerous recent advances in spatial econometrics, the choice of spatial weights remains exogenously determined by the researcher in empirical applications. Bayesian techniques provide statistical evidence regarding the simultaneous choice of model specification and spatial weights matrices by using posterior probabilities. This paper demonstrate the Bayesian estimation approach in a spatial hedonic property model estimating the impacts of repeated wildfires on house prices in Southern California. We find that improper choice of spatial model and weights can result in up to 5 percent difference in estimated coefficients and in our case study up to a $15 Million difference in total benefits of reducing wildfires in Los Angeles County.
Highlights
Evaluating the effects of residential area environmental amenities, land uses, and hazards on society has frequently involved using differences in house prices to reveal the marginal benefits or costs to households
In this paper we address an important issue in spatial hedonic property models—how to simultaneously choose the spatial weights and corresponding spatial model specification
Bayesian techniques can provide statistical evidence regarding the simultaneous choice of spatial model specification and spatial weights matrices in spatial econometrics, while more commonly applied Maximum Likelihood (ML) techniques do not allow non-nested model comparison
Summary
Evaluating the effects of residential area environmental amenities, land uses, and hazards on society has frequently involved using differences in house prices to reveal the marginal benefits or costs to households The results of these hedonic property estimations are often incorporated into benefit-cost analyses with policy implications. When comparing results from Maximum Likelihood estimations to those from General Method of Moments, Bell and Bockstael (2000) found that coefficient estimates from a spatial hedonic property model were more sensitive to the choice of weighting matrix than to the method of estimation. They compared 10 coefficients estimated with 6 different weighting matrices and calculated a percent difference in coefficients equal to the difference in the estimates divided by the mean of the two estimates. To the authors’ knowledge, this is the first application of Bayesian methods to simultaneously inform model choice and spatial weights matrix choice in a hedonic property model
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
