CFDP Revision Date
We present new identiﬁcation results for nonparametric models of diﬀerentiated products markets, using only market level observables. We specify a nonparametric random utility discrete choice model of demand allowing rich preference heterogeneity, product/market unobservables, and endogenous prices. Our supply model posits nonparametric cost functions, allows latent costs shocks, and nests a range of standard oligopoly models. We consider identiﬁcation of demand, identiﬁcation of changes in aggregate consumer welfare, identiﬁcation of marginal costs, identiﬁcation of ﬁrms’ marginal cost functions, and discrimination between alternative models of ﬁrm conduct. We explore two complementary approaches. The ﬁrst demonstrates identiﬁcation under the same nonparametric instrumental variables conditions required for identiﬁcation of regression models. The second treats demand and supply in a system of nonparametric simultaneous equations, leading to constructive proofs exploiting exogenous variation in demand shifters and cost shifters. We also derive testable restrictions that provide the ﬁrst general formalization of Bresnahan’s (1981, 1982) intuition for empirically distinguishing between alternative models of oligopoly competition. From a practical perspective, our results clarify the types of instrumental variables needed with market level data, including tradeoﬀs between functional form and exclusion restrictions.
Berry, Steven T. and Haile, Philip A., "Identification in Differentiated Products Markets Using Market Level Data" (2010). Cowles Foundation Discussion Papers. 2071.