Estimation of Beauty Contest Auctions
46 Pages Posted: 14 Apr 2013 Last revised: 23 Dec 2014
Date Written: December 22, 2014
Beauty contests are auction mechanisms used to buy-or-sell differentiated products. Beauty contests are widely used in procuring welfare-to-work projects, freelance services, in selling online ads, in real-estate transactions, and in hiring, dating/marriage decisions. Unlike price-only auctions, beauty contests have no closed-form bidding strategies and suffer from non-multiplicatively separable unobserved auction heterogeneity, which makes their estimation challenging. To address these challenges, we formulate beauty contests as incomplete information games and present a two-step method to estimate them. A key contribution of our method is its ability to account for common-knowledge auction-specific unobservables in the context of two-step methods using finite unobserved types. We show that unobserved auction types and distributions of bids are non-parametrically identified and recoverable in the first step using a nonparametric EM-like algorithm, and this can then be used in the second step to recover cost distributions. We present an application of our method in the online freelancing context. We find that seller margins/market-power in this marketplace are around 15%; and that not accounting for unobserved heterogeneity can significantly bias estimates of costs in this setting. Based on our estimates, we run counterfactual simulations and provide guidelines to managers of freelance firms.
Keywords: auction, structural model, unobserved heterogeneity, nonparametric, EM algorithm
JEL Classification: D44, J30, L14, M31, C14, C61
Suggested Citation: Suggested Citation
By Peter Rossi