Jump to Main Content
Identification of first-price auctions with non-equilibrium beliefs: A measurement error approach
- An, Yonghong
- Journal of econometrics 2017 v.200 no.2 pp. 326-343
- USDA Forest Service, auctions, econometric models, economic analysis, economic theory, forest trees, United States
- This paper studies identification and estimation of two models for first-price auctions: (1) bidders’ beliefs about their opponents’ bidding behavior are not in equilibrium but follow “level-k” thinking, and (2) bidders’ values are asymmetrically distributed. Exploiting the nonparametric methodology developed for measurement error models (e.g., Hu, 2008), we show that both models can be identified by a unified methodology. The proposed methodology is applied to US Forest Service timber auction data and the estimation results suggest that bidders hold heterogeneous and non-equilibrium beliefs.