Working Paper: NBER ID: w12126
Authors: Susan Athey; Philip A. Haile
Abstract: Many important economic questions arising in auctions can be answered only with knowledge of the underlying primitive distributions governing bidder demand and information. An active literature has developed aiming to estimate these primitives by exploiting restrictions from economic theory as part of the econometric model used to interpret auction data. We review some highlights of this recent literature, focusing on identification and empirical applications. We describe three insights that underlie much of the recent methodological progress in this area and discuss some of the ways these insights have been extended to richer models allowing more convincing empirical applications. We discuss several recent empirical studies using these methods to address a range of important economic questions.
Keywords: Auctions; Econometrics; Identification
JEL Codes: C5; L1; D4
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| Identification of underlying distributions (C46) | Observation of order statistics (C69) |
| Observation of order statistics (C69) | Understanding bidder valuations (D44) |
| Winning bid (D44) | Distribution of valuations (D39) |
| Equilibrium conditions (C62) | Insights into bidder strategies (D44) |
| Winners' curse (D44) | Bidding strategies (D44) |
| Increased competition among bidders (D44) | Magnitude of the winners' curse (D44) |
| Distinction between private and common values models (D46) | Empirical testing (C90) |
| Observed bidding behavior (D44) | Discrimination between models (C52) |
| Auction outcomes (D44) | Discrimination between models (C52) |