Nonparametric kernel estimation of Weibull-tail coefficient in presence of the right random censoring

TL;DR

This paper develops nonparametric methods to estimate the Weibull-tail coefficient under right censoring, introduces a Weissman-type estimator for extreme quantiles, and demonstrates their effectiveness through simulations and real data analysis.

Contribution

It proposes new nonparametric estimators for Weibull-tail coefficients with right censored data and extends extreme quantile estimation using a Weissman-type approach.

Findings

Estimators perform well in finite samples in simulations.

The methodology is applicable to real-world censored data.

Comparison shows advantages over existing strategies.

Abstract

In this paper, nonparametric estimation of the conditional Weibull-tail coefficient when the variable of interest is right random censored is addressed. A Weissman-type estimator of conditional extreme quantile is also proposed. In addition, a simulation study is conducted to assess the finite-sample behavior of the proposed estimators and a comparison with alternative strategies is provided. Finally, the practical applicability of the methodology is presented using a real datasets of men suffering from a larynx cancer.