Identification of Auction Models Using Order Statistics

Abstract

Auction data often fail to record all bids or all relevant factors that shift bidder values. In this paper, we study the identification of auction models with unobserved heterogeneity (UH) using multiple order statistics of bids. Classical measurement error approaches require multiple independent measurements. Order statistics, by definition, are dependent, rendering classical approaches inapplicable. First, we show that models with nonseparable finite UH is identifiable using three consecutive order statistics or two consecutive ones with an instrument. Second, two arbitrary order statistics identify the models if UH provides support variations. Third, models with separable continuous UH are identifiable using two consecutive order statistics under a weak restrictive stochastic dominance condition. Lastly, we apply our methods to U.S. Forest Service timber auctions and find evidence of UH.