Identification in Auction Models with Interdependent Costs

This paper provides a nonparametric identification result for procurement models with asymmetric bidders, dependent private information, and interdependent costs. For risk-neutral bidders, the model’s payoff-relevant primitives are the joint distribution of private information and each bidder’s full-information expected cost. The joint distribution of bids identifies the joint distribution of signals. First-order conditions identify the expected cost conditional on tying with at least one competitor for the lowest bid. I show identification of each bidder’s full-information cost, using variation in competitors’ cost shifters that are excludable from bidders’ own full-information costs, and generate variation in the set of competitors’ signals that induce a tie for the lowest bid. I estimate the relevant payoff primitives using data from Michigan highway procurements and evaluate policies that affect the winner’s curse’s severity.