Výsledky vyhledávání

Report

Functional kernel estimators of conditional extreme quantiles

Autor: Gardes, L., Girard, S.

Publikováno v: Recent advances in functional data analysis and related topics (2011) 135--140

We address the estimation of "extreme" conditional quantiles i.e. when their order converges to one as the sample size increases. Conditions on the rate of convergence of their order to one are provided to obtain asymptotically Gaussian distributed k

Externí odkaz: http://arxiv.org/abs/1212.1076

Zobrazit plný text záznamu

Report

A moving window approach for nonparametric estimation of the conditional tail index

Autor: Gardes, L., Girard, S.

Publikováno v: Journal of Multivariate Analysis, 99, 2368-2388 (2008)

We present a nonparametric family of estimators for the tail index of a Pareto-type distribution when covariate information is available. Our estimators are based on a weighted sum of the log-spacings between some selected observations. This selectio

Externí odkaz: http://arxiv.org/abs/1104.0763

Zobrazit plný text záznamu

Report

Functional nonparametric estimation of conditional extreme quantiles

Autor: Gardes, L., Girard, S., Lekina, A.

Publikováno v: Journal of Multivariate Analysis, 101, 419-433, 2010

We address the estimation of quantiles from heavy-tailed distributions when functional covariate information is available and in the case where the order of the quantile converges to one as the sample size increases. Such "extreme" quantiles can be l

Externí odkaz: http://arxiv.org/abs/1104.0166

Zobrazit plný text záznamu

Report

Bias-reduced estimators of the Weibull tail-coefficient

Autor: Diebolt, J., Gardes, L., Girard, S., Guillou, A.

Publikováno v: Test, 17, 311-331, 2008

In this paper, we consider the problem of the estimation of a Weibull tail-coefficient. In particular, we propose a regression model, from which we derive a bias-reduced estimator. This estimator is based on a least-squares approach. The asymptotic n

Externí odkaz: http://arxiv.org/abs/1103.6172

Zobrazit plný text záznamu

Report

Gaussian Regularized Sliced Inverse Regression

Autor: Bernard-Michel, C., Gardes, L., Girard, S.

Publikováno v: Statistics and Computing 19, 85-98 (2009)

Sliced Inverse Regression (SIR) is an effective method for dimension reduction in high-dimensional regression problems. The original method, however, requires the inversion of the predictors covariance matrix. In case of collinearity between these pr

Externí odkaz: http://arxiv.org/abs/1103.6118

Zobrazit plný text záznamu