Nonparametric estimation of the conditional tail index and extreme quantiles under random censoring

Pathé Ndao (1) , Aliou Diop (1) , Jean-François Dupuy (2)

1 LERSTAD - laboratoire d'Etudes et de recherches en Statistiques et Développement
2 IRMAR - Institut de Recherche Mathématique de Rennes

In this paper, we investigate the estimation of the tail index and extreme quantiles of a heavy-tailed distribution when some covariate information is available and the data are randomly right-censored. We construct several estimators by combining a moving-window technique (for tackling the covariate information) and the inverse probability-of-censoring weighting method, and we establish their asymptotic normality. A comprehensive simulation study is conducted to evaluate the finite-sample performance of the proposed estimators and to identify their application scope.

Mots clés: conditional extreme quantiles; conditional extreme value index; Random censoring; heavy-tailed distribution; moving window; simulations

Domaines: Méthodologie [stat.ME]

Pathé Ndao, Aliou Diop, Jean-François Dupuy. Nonparametric estimation of the conditional tail index and extreme quantiles under random censoring. Computational Statistics and Data Analysis, 2014, 79, pp.63-79. ⟨10.1016/j.csda.2014.05.007⟩. ⟨hal-00802804⟩