On the accuracy of inference on heavy-tailed distributions

Novak, Serguei (2013) On the accuracy of inference on heavy-tailed distributions. Theory of Probability and Its Applications, 58 (3). pp. 509-518. ISSN 0040-585X

[img]
Preview
PDF - Final accepted version (with author's formatting)
Download (128kB) | Preview

Abstract

This paper suggests a simple method of deriving nonparametric lower bounds of the accuracy of statistical inference on heavy-tailed distributions. We present lower bounds of the mean squared error of the tail index, the tail constant, and extreme quantiles estimators. The results show that the normalizing sequences of robust estimators must depend in a specific way on the tail index and the tail constant.

Item Type: Article
Additional Information: Published online: 16 September 2014
Research Areas: A. > School of Science and Technology > Design Engineering and Mathematics
Item ID: 18124
Notes on copyright: Published in Theory of Probability & Its Applications in Volume 58, Issue 3, published by the Society of Industrial and Applied Mathematics (SIAM). Copyright © 2014 Society of Industrial and Applied Mathematics.
Useful Links:
Depositing User: Serguei Novak
Date Deposited: 14 Oct 2015 10:00
Last Modified: 31 May 2019 08:44
URI: https://eprints.mdx.ac.uk/id/eprint/18124

Actions (login required)

Edit Item Edit Item

Full text downloads (NB count will be zero if no full text documents are attached to the record)

Downloads per month over the past year