Nonparametric Identification of Multinomial Choice Demand Models with Heterogeneous Consumers

Joint with: Steven T. Berry, Yale University

We consider identification of nonparametric random utility models of multinomial choice using observation of consumer choices. Our model of preferences nests random coefficients

discrete choice models widely used in practice with parametric functional form and dis-tributional assumptions. However, our model is nonparametric and distribution free. It incorporates choice-specific unobservables, endogenous choice characteristics, unknown heteroskedasticity, and correlated taste shocks. We consider full identification of the random utility model as well as identification of demand. Under standard orthogonality, "large support," and instrumental variables assumptions, we show identifiability of choice-specific

unobservables and the joint distribution of preferences conditional on any vector of observed and unobserved characteristics. We demonstrate robustness of these results to relaxation of the large support condition and show that when this condition is replaced with a much

weaker "common choice probability" condition, the demand structure is still identified. We also show that key maintained hypotheses are testable.

For more information, contact Petra Todd.