A functional estimation approach to the first-price auction models

This paper introduces new methods of identification and estimation the first-price sealed bid auction model compares them with previous existing ones. The first method allows us to estimate directly (through an iterative algorithm) cumulative distribution function private values without estimating beforehand. In second method, we use a quantile approach. Although is complex nonlinear inverse problem, leads linearization model. Thus, in contrast are able deduce closed-form solution for values. constructive one-stage procedure that can be performed using three regularization methods: Tikhonov regularization, Landweber–Friedman kernels. We conduct Monte Carlo experiment compare our by c.d.f. quantiles developed Guerre et al. (2000), Marmer Shneyerov (2012), Hickman Hubbard (2015). Some extensions considered: asymmetric bidders, affiliation, conditional models exogenuous variables, observation only winning bids.