Inferences on parametric estimation of distribution tails (Q2304357)

The authors propose a general method for parameter estimation of a distribution tail that does not depend on the fulfillment of the conditions of the Fisher-Tipett-Gnedenko theorem and the Pickands-Balkema-de Haan theorem. The consistency of the proposed estimator and its asymptotic normality under stronger conditions imposed on the parametric family of distribution tails is proved. The proposed method is discussed for the Weibull distribution.