The Econometrics of Auctions with Asymmetric Anonymous Bidders

We consider standard auction models when bidders' identities arenot observed by the econometrician. First, we adapt the denition ofidentiability to a framework with anonymous bids and we explore theextent to which anonymity reduces the possibility to identify privatevalue auction models. Second, in the asymmetric independent privatevalue model which is nonparametrically identied, we adapt Guerre,Perrigne and Vuong [10]'s two-stage estimation procedure. Our multistagekernel-based estimator achieves the optimal uniform convergencerate when identities are observed.