A0185
Title: Asymptotically unbiased estimator of the extreme value index under random censoring
Authors: Armelle Guillou - Strasbourg University (France) [presenting]
Martin Bladt - University of Copenhagen (Denmark)
Yuri Goegebeur - University of Southern Denmark (Denmark)
Abstract: The purpose is to consider bias-corrected estimation of the extreme value index of a Pareto-type distribution in the censoring framework. The initial estimator is based on a Kaplan-Meier integral from which the bias is removed under a second-order framework. This estimator depends on a suitable external estimation of second-order parameters, which is also discussed. The weak convergence of the bias-corrected estimator is established. It has the nice property of having the same asymptotic variance as the initial estimator. This nice feature is illustrated in a simulation study where the estimator is compared to alternatives already introduced in the literature. Finally, the methodology is applied to an insurance dataset.
