Extreme expectile estimation for short-tailed data

The use of expectiles in risk management contexts has recently gathered substantial momentum because of their excellent axiomatic and probabilistic properties. While expectile estimation at central levels already has a substantial history, expectile estimation at extreme levels has so far only been considered when the underlying distribution has a heavy right tail. This article focuses on the challenging short-tailed setting when the distribution of the variable of interest has a negative extreme value index and is bounded to the right. We derive an asymptotic expansion of extreme expectiles in this context under a general second-order extreme value condition. This asymptotic expansion makes it possible to study two semiparametric estimators of extreme expectiles, whose asymptotic properties we obtain in a general model of strictly stationary but weakly dependent observations. A simulation study and real data analysis illustrate the performance of the proposed statistical techniques.