Nonparametric identification in asymmetric second-price auctions: a new approach

This paper proposes an approach to proving nonparametric identification in gen- eralized competing risks models. I focus on second-price auctions, which constitute a special case of these models, and analyze the identification of asymmetric distri- butions of bidders' values. I consider the situation where bidders have independent private values, and the only available data pertain to the winner's identity and to the winning price. I provide conditions on observable data sufficient to guarantee point identification. My identification proof is constructive and based on establishing the existence and uniqueness of a solution to the system of non-linear differential equa- tions that describes the relationships between unknown distribution functions and observable functions. I demonstrate how this approach can be extended to obtain identification in any generalized competing risks model. Moreover, contrary to classi- cal competing risks (Roy model) results, I describe how generalized models can yield implications that can help check for model misspecification.