An estimator for the tail index of an integrated conditional Pareto-Weibull-type model

Y. Goegebeur; A. Guillou; M. Osmann

doi:10.1016/j.spl.2015.04.008

An estimator for the tail index of an integrated conditional Pareto-Weibull-type model

Y. Goegebeur, A. Guillou, M. Osmann

Institut for Matematik og Datalogi

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › peer review

Abstract

We introduce a nonparametric regression estimator for a tail heaviness parameter in an integrated conditional Pareto-Weibull-type model. The estimator is based on local log excesses over a high random threshold. Asymptotic properties are derived under proper regularity conditions.

Originalsprog	Engelsk
Tidsskrift	Statistics & Probability Letters
Vol/bind	103
Sider (fra-til)	8-16
ISSN	0167-7152
DOI	https://doi.org/10.1016/j.spl.2015.04.008
Status	Udgivet - 2015

Dokumenter og links

10.1016/j.spl.2015.04.008

https://hal.archives-ouvertes.fr/hal-01312904/document

Citationsformater

@article{b0d2271bce094f24ab6b8b1ca2f06f96,

title = "An estimator for the tail index of an integrated conditional Pareto-Weibull-type model",

abstract = "We introduce a nonparametric regression estimator for a tail heaviness parameter in an integrated conditional Pareto-Weibull-type model. The estimator is based on local log excesses over a high random threshold. Asymptotic properties are derived under proper regularity conditions.",

keywords = "Extremes, Local estimation, Regression, Tail index",

author = "Y. Goegebeur and A. Guillou and M. Osmann",

year = "2015",

doi = "10.1016/j.spl.2015.04.008",

language = "English",

volume = "103",

pages = "8--16",

journal = "Statistics & Probability Letters",

issn = "0167-7152",

publisher = "Elsevier",

}

TY - JOUR

T1 - An estimator for the tail index of an integrated conditional Pareto-Weibull-type model

AU - Goegebeur, Y.

AU - Guillou, A.

AU - Osmann, M.

PY - 2015

Y1 - 2015

N2 - We introduce a nonparametric regression estimator for a tail heaviness parameter in an integrated conditional Pareto-Weibull-type model. The estimator is based on local log excesses over a high random threshold. Asymptotic properties are derived under proper regularity conditions.

AB - We introduce a nonparametric regression estimator for a tail heaviness parameter in an integrated conditional Pareto-Weibull-type model. The estimator is based on local log excesses over a high random threshold. Asymptotic properties are derived under proper regularity conditions.

KW - Extremes

KW - Local estimation

KW - Regression

KW - Tail index

U2 - 10.1016/j.spl.2015.04.008

DO - 10.1016/j.spl.2015.04.008

M3 - Journal article

SN - 0167-7152

VL - 103

SP - 8

EP - 16

JO - Statistics & Probability Letters

JF - Statistics & Probability Letters

ER -

An estimator for the tail index of an integrated conditional Pareto-Weibull-type model

Abstract

Dokumenter og links

Fingeraftryk

Citationsformater