We establish Edgeworth expansions for the distribution function of the standardized Hill estimator for the reciprocal of the index of regular variation of the tail of a distribution function. The expansions are used to derive expansions for coverage probabilities of confidence intervals for the tail index based on the Hill estimator.
Publié le : 2007-02-14
Classification:
asymptotic normality,
confidence intervals,
Edgeworth expansions,
extreme value index,
Hill estimator,
regular variation,
tail index
@article{1175287728,
author = {Haeusler, Erich and Segers, Johan},
title = {Assessing confidence intervals for the tail index by Edgeworth expansions for the Hill estimator},
journal = {Bernoulli},
volume = {13},
number = {1},
year = {2007},
pages = { 175-194},
language = {en},
url = {http://dml.mathdoc.fr/item/1175287728}
}
Haeusler, Erich; Segers, Johan. Assessing confidence intervals for the tail index by Edgeworth expansions for the Hill estimator. Bernoulli, Tome 13 (2007) no. 1, pp. 175-194. http://gdmltest.u-ga.fr/item/1175287728/