Title: Robust estimation of the Pickands dependence function under random right censoring
Authors: Yuri Goegebeur - University of Southern Denmark (Denmark) [presenting]
Armelle Guillou - Strasbourg university (France)
Jing Qin - University of Southern Denmark (Denmark)
Abstract: Robust nonparametric estimation of the Pickands dependence function under random right censoring is considered. The estimator is obtained by applying the minimum density power divergence criterion to properly transformed bivariate observations. The asymptotic properties are investigated by making use of results for Kaplan-Meier integrals. We investigate the finite sample properties of the proposed estimator with a simulation experiment and illustrate its practical applicability on a dataset of insurance indemnity losses.