Nonparametric Identification and Inference of First-Price Auctions with Heterogeneous Bidders

Abstract

In the auction literature, it is well established that bidders' asymmetry plays an important role in determining auction revenues. In this paper, we propose a nonparametric methodology to analyze first-price auctions with two popularly adopted asymmetries: heterogeneous risk preferences and asymmetric value distributions. We find that the two competing models provide distinct implications for the bid distributions conditional on heterogeneity. By modeling bidders' asymmetry as unobserved heterogeneity, we show that the conditional bid distributions are identified nonparametrically. These results enable researchers to distinguish between the two competing models. The Monte Carlo experiments demonstrate the good performance of the proposed method. In an application using the US Forest Service timber auction data, we find that the data support the model with heterogeneity in risk preference.