Using Panel Data to Easily Estimate Hedonic Demand Functions

Abstract

The hedonics literature has often asserted that if one were able to observe the same individual make multiple purchase decisions, one could recover rich estimates of preferences for a given amenity. In particular, in the face of a changing price schedule, observing each individual twice is sufficient to recover the underlying (linear) demand function separately for each individual, with no restrictions on this heterogeneity in either the intercept or the slope. Using a rich panel dataset, we recover the full distribution of demand functions for clean air in the Bay Area of California. First, we find that estimating the full demand function, rather than simply recovering an estimate of local marginal willingness to pay, is important. Second, we find evidence of considerable heterogeneity in these functions and find that this heterogeneity is important from a policy perspective -- our data-driven estimates of the welfare effects associated with a non-marginal change in air quality differ substantially from the existing approaches to welfare estimation.