Working Paper: NBER ID: w24795
Authors: Giovanni Compiani; Philip Haile; Marcelo Santanna
Abstract: An oil lease auction is the classic example motivating a common values model. However, formal testing for common values has been hindered by unobserved auction-level heterogeneity, which is likely to affect both participation in an auction and bidders’ willingness to pay. We develop and apply an empirical approach for first-price sealed bid auctions with affiliated values, unobserved heterogeneity, and endogenous bidder entry. The approach also accommodates spatial dependence and sample selection. Following Haile, Hong and Shum (2003), we specify a reduced form for bidder entry outcomes and rely on an instrument for entry. However, we relax their control function requirements and demonstrate that our specification is generated by a fully specified game motivated by our application. We show that important features of the model are nonparametrically identified and propose a semiparametric estimation approach designed to scale well to the moderate sample sizes typically encountered in practice. Our empirical results show that common values, affiliated private information, and unobserved heterogeneity—three distinct phenomena with different implications for policy and empirical work—are all present and important in U.S. offshore oil and gas lease auctions. We find that ignoring unobserved heterogeneity in the empirical model obscures the presence of common values. We also examine the interaction between affiliation, the winner’s curse, and the number of bidders in determining the aggressiveness of bidding and seller revenue
Keywords: Auction Theory; Oil Lease Auctions; Common Values; Unobserved Heterogeneity
JEL Codes: L0
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| Unobserved heterogeneity (C21) | Bidder entry (D44) |
| Unobserved heterogeneity (C21) | Bidding behavior (D44) |
| Number of bidders (D44) | Bidding aggressiveness (D44) |
| Number of bidders (D44) | Seller revenue (L85) |
| Bidder entry (D44) | Bidding behavior (D44) |
| Unobserved heterogeneity (C21) | Common values (D46) |
| Unobserved heterogeneity (C21) | Affiliated private information (D82) |
| Unobserved heterogeneity (C21) | Erroneous conclusions about bidders' market power (D44) |
| Unobserved heterogeneity (C21) | Optimal auction design (D44) |