Semiparametric estimation of the optimal reserve price in first-price auctions

The optimal reserve price in the independent private value paradigm is generally expressed as a functional of the latent distribution of private signals, which is by nature unobserved. This feature has limited the implementation of the optimal reserve price in practice. In this article, we consider first-price auctions within the general affiliated private values paradigm. We show that the seller's expected profit can be written as a functional of the observed bid distribution. We propose a semiparametric extremum estimator for estimating consistently the optimal reserve price from observed bids. As an illustration, we consider the Outer Continental Shelf (OCS) wildcat auctions.