| Abstract | In this paper we are interested in the asymptotic comparison of a set of semi-parametric minimum variance reduced-bias (MVRB) tail index estimators, at optimal levels and for a wide class of models. Again, as in the classical case, there is not any estimator that can always dominate the alternatives, but interesting clearcut patterns are found. Consequently, and in practice, a suitable choice of a set of tail index estimators, will jointly enable us to better estimate the tail index γ, the primary parameter of extreme events. |
