Identification and Inference in First-Price Auctions with Risk-Averse Bidders and Selective Entry

We study identification and inference in first-price auctions with risk averse bidders and selective entry, building on a flexible entry and bidding framework we call the Affiliated Signal with Risk Aversion (AS-RA) model. Assuming that the econometrician observes either exogenous variation in the number of potential bidders or a continuous instrument shifting opportunity costs of entry, we provide a sharp characterization of the nonparametric restrictions implied by equilibrium bidding. Given variation in either competition or costs, this characterization implies that risk neutrality is generically testable in the sense that if bidders are strictly risk averse, then no risk neutral model can rationalize the data. Furthermore, if the cost instrument induces sufficient variation in entry, then the model is nonparametrically identified. We then consider semiparametric identification and inference when pre-entry signals are linked to post-entry values by a parametric copula. We show that the AS-RA model is conditionally identified up to the parameters of this copula, and building on this propose a novel approach to robust semiparametric inference within the AS-RA model