A Non–stationary Non-gaussian Hedonic Spatial Model for House Selling Prices a Non–stationary Non-gaussian Hedonic Spatial Model for House Selling Prices

This work proposes a hedonic random field model to describe house selling prices over the period 2000– 2005 in Cedar Falls, Iowa. This real estate market presents two distinctive features that are not described by commonly used stationary Gaussian random field models: (a) the city encompasses within its limits a hog lot which acts as an externality, negatively affecting the selling price of nearby houses, and (b) the distribution of house selling prices displays heavy tails. A non-stationary and non-Gaussian random field model is constructed by multiplying two independent Gaussian random fields, where the factors are tailored so the resulting model describes the aforementioned distinctive features. We also propose an empirical diagnostic to assess the fit of the proposed model to a given dataset.