Frontier estimation with kernel regression on high order moments
Résumé
We present a new method for estimating the frontier of a multidimensional sample when the conditional distribution function decreases at a polynomial rate to zero in the neighborhood of the frontier. The estimator is based on a kernel regression on high moments. It is assumed that the order of the moments goes to infinity while the bandwidth of the kernel goes to zero. We give conditions on these two parameters to obtain the asymptotic normality of the estimator. The good performance of the estimator is illustrated on some finite sample situations.
Origine : Fichiers produits par l'(les) auteur(s)