Résumé
We propose a general bootstrap technique for estimating the Pareto-index. The method is based on the resampling of a sample of size ℓ(
n) deduced from the original sample
X
1,…,
X
n
, where ℓ(
n) is a sequence of positive integers satisfying some regularity conditions. We show that this new procedure works for estimators based on the largest values of the original sample.