We are grateful to a co-editor and three anonymous referees for their constructive comments that have greatly improved the paper. We also thank Yanqin Fan, Jeremy Fox, James Heckman, Martin Pesendorfer, and participants in seminars at Tillburg University, Toulouse School of Economics, University of Southern California, National University of Singapore, Singapore Management University, HKUST, Columbia University, UBC, University of Pennsylvania, Carnegie Mellon University, Penn State University, and at the EC2 Conference on Identification in Econometrics in Toulouse, December 2010, the North American Summer Meeting of the Econometric Society in St. Louis, June 2011, the European Meeting of the Econometric Society in Oslo, August 2011, and the Identification and Inference in Econometrics Conference at Vanderbilt University, March 2012, for helpful comments and discussion. Support from the National Science Foundation (SES-0922109) is gratefully acknowledged. Previous versions of the paper were circulated under the title “Partial Identification in Auctions With Selective Entry.”
Identification in Auctions With Selective Entry
Version of Record online: 5 FEB 2014
© 2014 The Econometric Society
Volume 82, Issue 1, pages 315–344, January 2014
How to Cite
Gentry, M. and Li, T. (2014), Identification in Auctions With Selective Entry. Econometrica, 82: 315–344. doi: 10.3982/ECTA10293
- Issue online: 5 FEB 2014
- Version of Record online: 5 FEB 2014
- Manuscript received September, 2011; final revision received July, 2013.
- endogenous participation;
This paper considers nonparametric identification of a two-stage entry and bidding game we call the Affiliated-Signal (AS) model. This model assumes that potential bidders have private values, observe signals of their values prior to entry, and then choose whether to undertake a costly entry process, but imposes only minimal structure on the relationship between signals and values. It thereby nests a wide range of entry processes, including in particular the Samuelson (1985) and Levin and Smith (1994) models as special cases. Working within the AS model, we map variation in factors affecting entry behavior (potential competition or entry costs) into identified bounds on model fundamentals. These bounds are constructive, collapse to point identification when available entry variation is continuous, and can readily be refined to produce the pointwise sharp identified set. We then extend our core results to accommodate nonseparable unobserved auction-level heterogeneity and potential endogeneity of entry shifters, thereby establishing a formal identification framework for structural analysis of auctions with selective entry.