Identification in Differentiated Products Markets Using Market Level Data

We consider nonparametric identification in models of differentiated products markets, using only market level observables. On the demand side we consider a nonparametric random utility model nesting random coefficients discrete choice models widely used in applied work. We allow for product/market-specific unobservables, endogenous product characteristics (e.g., prices), and high-dimensional taste shocks with arbitrary correlation and heteroskedasticity. On the supply side we specify marginal costs nonparametrically, allow for unobserved firm heterogeneity, and nest a variety of equilibrium oligopoly models. We pursue two approaches to identification. One relies on instrumental variables conditions used previously to demonstrate identification in a nonparametric regression framework. With this approach we can show identification of the demand side without reference to a particular supply model. Adding the supply side allows identification of firms' marginal costs as well. Our second approach, more closely linked to classical identification arguments for supply and demand models, employs a change of variables approach. This leads to constructive identification results relying on exclusion and support conditions. Our results lead to a testable restriction that provides the first general formalization of Bresnahan's (1982) intuition for empirically discriminating between alternative models of oligopoly competition