Frontier estimation with kernel regression on high order moments

Stephane Girard 1 Armelle Guillou 2 Gilles Stupfler 2
1 MISTIS - Modelling and Inference of Complex and Structured Stochastic Systems
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : We present a new method for estimating the frontier of a multidimensional sample. The estimator is based on a kernel regression on high order moments. It is assumed that the order of the moments goes to infinity while the bandwidth of the kernel goes to zero. The consistency of the estimator is proved under mild conditions on these two parameters. The asymptotic normality is also established when the conditional distribution function decreases at a polynomial rate to zero in the neighborhood of the frontier. The good performance of the estimator is illustrated on some finite sample situations.
Document type :
Journal articles
Journal of Multivariate Analysis, Elsevier, 2013, 116, pp.172-189. 〈10.1016/j.jmva.2012.12.001〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00499369
Contributor : Stephane Girard <>
Submitted on : Monday, November 26, 2012 - 10:00:36 AM
Last modification on : Friday, November 17, 2017 - 4:20:03 PM
Document(s) archivé(s) le : Wednesday, February 27, 2013 - 3:42:27 AM

File

Frontier_revised3.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Stephane Girard, Armelle Guillou, Gilles Stupfler. Frontier estimation with kernel regression on high order moments. Journal of Multivariate Analysis, Elsevier, 2013, 116, pp.172-189. 〈10.1016/j.jmva.2012.12.001〉. 〈hal-00499369v3〉

Share

Metrics

Record views

510

Document downloads

197