This master class has been organised in partnership with The ESRC Centre for Economic Learning and Social Evaluation (ELSE).
Auctions provide opportunities for economists to examine field data from markets that can involve rich strategic interaction and asymmetric information while nonetheless being simple enough that the salient forces can be convincingly captured by a tractable economic model. Consequently, auctions have been at the center of efforts to combine economic theory with econometric analysis to understand behavior and inform policy.
Remarkably, much of what can be learned from auction data can be learned without restrictions beyond those derived from economic theory. In particular, identification of model primitives or testing of important economic hypotheses often does not depend on unverifiable parametric distributional assumptions.
The masterclases will discuss recent developments in structural econometric approaches to auctions, with an emphasis on nonparametric identification, i.e., on how auction observables and the implications of economic theory can be combined to enable researchers to uncover the primitive functions that characterize bidder demand and information. A wide range of demand and information structures (e.g., private and common values) will be covered, as will a variety of types of data one is likely to encounter in practice.
Most of the discussion will concern first-price sealed-bid and ascending auctions, which are the most common auction forms in practice and which present very different challenges to empirical work. Parametric, semiparametric, and nonparametric estimation and testing approaches will also be discussed, as will examples of empirical work applying these methods.