Estimating Hedonic Functions for Rents and Values in the Presence of Unobserved Heterogeneity in the Quality for Housing

A central challenge in estimating models with heterogeneous housing is separating quality from price. We provide a new method for estimating hedonic functions for rental rates and housing values treating housing quality as unobserved by the econo- metrician. Our method also deals with the problem that rental prices and housing values are partially latent showing that the rent-to-value ratio is non-parameterically identified. We, thus provide an integrated treatment of non-linear pricing rental and asset markets. Our new method can be used to gain some new insights into the causes and effects of the recent housing market crisis in the U.S. Our main application focuses on the housing markets of Miami (Fl) which experienced an average real appreciation of housing values of 65 percent during the period from 2002 to 2007. Our findings are broadly consistent with the view that changes in credit market conditions for low income houses together with changes in investor expectations about future housing prices may have accounted for the large run-up in housing values.