Using 70,822 observations on housing prices from 1969 to 1991 from Fai
rfax County Virginia, this article demonstrates the substantial benefi
ts obtained by modeling the spatial as well as the temporal dependence
of the data. Specifically, the spatiotemporal autoregression with twe
lve variables reduced median absolute error by 37.35% relative to an i
ndicator-based model with twenty-six variables. One-step ahead forecas
ts also document the improved performance of the proposed spatiotempor
al model. In addition, the article illustrates techniques for rapidly
computing the estimates and shows how to compute indices for any locat
ion.