A general estimator for the right endpoint - with an application to supercentenarian women's records

We extend the right endpoint estimator introduced in Fraga Alves and Neves (Statist. Sinica 24:1811--1835, 2014) to a suitable endpoint estimator for any light-tailed distribution function belonging to some domain of attraction induced by the extreme value theorem. This stretch enables a general estimator of the finite right endpoint, which does not require estimation of the (supposedly non-positive) extreme value index. The asymptotic properties of this endpoint estimator are derived and its finite sample performance evaluated by means of simulations. The latter conveys that the adopted endpoint estimator works remarkably well in case the true extreme value index stays above $-1/2$, embracing the most common cases in practical applications. An illustration is provided through a brief extreme value analysis of supercentenarian women data.