Skip to Main content Skip to Navigation
Conference papers

Nonparametric extremal quantile regression

Abdelaati Daouia 1 Laurent Gardes 2 Stephane Girard 3
3 MISTIS - Modelling and Inference of Complex and Structured Stochastic Systems
Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology, LJK - Laboratoire Jean Kuntzmann, Inria Grenoble - Rhône-Alpes
Abstract : Nonparametric regression quantiles obtained by inverting a kernel estimator of the conditional distribution of the response are long established in statistics [1,3,4]. Attention has been, however, restricted to ordinary quantiles staying away from the tails of the conditional distribution. The purpose of this paper is to extend their asymptotic theory into the tails. We focus on extremal quantile regression estimators of a response variable given a vector of covariates in the general setting, whether the conditional extreme-value index is positive, negative, or zero. Their limit distribution is established when they are located in the range of the data or near and even beyond the sample boundary, under technical conditions that link the speed of convergence of their order with the oscillations of the quantile function and a von-Mises property of the conditional distribution [2]. A simulation experiment and an illustration on American electric data are presented. [1] Berlinet, A., Gannoun, A. and Matzner-Lober, E. (2001) Asymptotic normality of convergent estimates of conditional quantiles, Statistics, 35, 139--169. [2] Daouia, A., Gardes, L. and Girard, S. (2013) On kernel smoothing for extremal quantile regression, Bernoulli, to appear. [3] Samanta, T. (1989) Non-parametric estimation of conditional quantiles, Statistics and Probability Letters, 7, 407--412. [4] Stute, W. (1986) Conditional empirical processes, The Annals of Statistics, 14, 638--647.
Complete list of metadata
Contributor : Stephane Girard <>
Submitted on : Monday, August 12, 2013 - 2:47:53 PM
Last modification on : Tuesday, February 9, 2021 - 3:20:20 PM


  • HAL Id : hal-00851124, version 1


Abdelaati Daouia, Laurent Gardes, Stephane Girard. Nonparametric extremal quantile regression. EVA 2013 - 8th International Conference on Extreme Value Analysis, Jul 2013, Shanghai, China. ⟨hal-00851124⟩



Record views