Empirical likelihood based inference for conditional Pareto-type tail index

We propose empirical likelihood-based statistics to construct confidence regions for the regression coefficient of the parametric tail index regression model. Our limited simulation study shows the method is more accurate than the normal approximation in terms of coverage probability. •The tail inde...

Full description

Saved in:
Bibliographic Details
Published in:Statistics & probability letters 2018-03, Vol.134, p.114-121
Main Authors: Ma, Yaolan, Jiang, Yuexiang, Huang, Wei
Format: Article
Language:English
Subjects:
Confidence regions
Empirical likelihood
Estimating equations
Pareto-type distribution
Tail index
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose empirical likelihood-based statistics to construct confidence regions for the regression coefficient of the parametric tail index regression model. Our limited simulation study shows the method is more accurate than the normal approximation in terms of coverage probability. •The tail index is an important parameter in the whole of extreme value theory.•The estimation of the Pareto-type conditional tail index is investigated.•Constructing confidence regions based on the empirical likelihood method.•Simulation results and a real application support superiority of our methods.
ISSN:0167-7152
1879-2103
DOI:10.1016/j.spl.2017.10.021