Estimating high quantiles plays an important role in the context of risk management. This involves extrapolation of an unknown distribution function. In this paper we propose three methods, namely, the normal approximation method, the likelihood ratio method and the data tilting method, to construct confidence regions for high quantiles of a heavy tailed distribution. A simulation study prefers the data tilting method.
Publié le : 2006-08-14
Classification:
Confidence region,
data tilting,
empirical likelihood method,
heavy tail,
high quantile,
62G32,
62G02
@article{1162567639,
author = {Peng, Liang and Qi, Yongcheng},
title = {Confidence regions for high quantiles of a heavy tailed distribution},
journal = {Ann. Statist.},
volume = {34},
number = {1},
year = {2006},
pages = { 1964-1986},
language = {en},
url = {http://dml.mathdoc.fr/item/1162567639}
}
Peng, Liang; Qi, Yongcheng. Confidence regions for high quantiles of a heavy tailed distribution. Ann. Statist., Tome 34 (2006) no. 1, pp. 1964-1986. http://gdmltest.u-ga.fr/item/1162567639/