Extremiles: a new perspective on asymmetric least squares

Quantiles and expectiles of a distribution are found to be useful descriptors of its tail in the same way as the median and mean are related to its central behavior. This paper considers a valuable alternative class to expectiles, called extremiles, which parallels the class of quantiles and include...

Full description

Bibliographic Details
Main Authors: Stupfler, Gilles, Daouia, Abdelaati, Gijbels, Irène
Format: Article
Published: Taylor & Francis 2019
Online Access:https://eprints.nottingham.ac.uk/52820/
_version_ 1848798817189625856
author Stupfler, Gilles
Daouia, Abdelaati
Gijbels, Irène
author_facet Stupfler, Gilles
Daouia, Abdelaati
Gijbels, Irène
author_sort Stupfler, Gilles
building Nottingham Research Data Repository
collection Online Access
description Quantiles and expectiles of a distribution are found to be useful descriptors of its tail in the same way as the median and mean are related to its central behavior. This paper considers a valuable alternative class to expectiles, called extremiles, which parallels the class of quantiles and includes the family of expected minima and expected maxima. The new class is motivated via several angles, which reveals its specific merits and strengths. Extremiles suggest better capability of fitting both location and spread in data points and provide an appropriate theory that better displays the interesting features of long-tailed distributions. We discuss their estimation in the range of the data and beyond the sample maximum. A number of motivating examples are given to illustrate the utility of estimated extremiles in modeling noncentral behavior. There is in particular an interesting connection with coherent measures of risk protection.
first_indexed 2025-11-14T20:25:48Z
format Article
id nottingham-52820
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T20:25:48Z
publishDate 2019
publisher Taylor & Francis
recordtype eprints
repository_type Digital Repository
spelling nottingham-528202020-05-04T19:46:46Z https://eprints.nottingham.ac.uk/52820/ Extremiles: a new perspective on asymmetric least squares Stupfler, Gilles Daouia, Abdelaati Gijbels, Irène Quantiles and expectiles of a distribution are found to be useful descriptors of its tail in the same way as the median and mean are related to its central behavior. This paper considers a valuable alternative class to expectiles, called extremiles, which parallels the class of quantiles and includes the family of expected minima and expected maxima. The new class is motivated via several angles, which reveals its specific merits and strengths. Extremiles suggest better capability of fitting both location and spread in data points and provide an appropriate theory that better displays the interesting features of long-tailed distributions. We discuss their estimation in the range of the data and beyond the sample maximum. A number of motivating examples are given to illustrate the utility of estimated extremiles in modeling noncentral behavior. There is in particular an interesting connection with coherent measures of risk protection. Taylor & Francis 2019 Article PeerReviewed Stupfler, Gilles, Daouia, Abdelaati and Gijbels, Irène (2019) Extremiles: a new perspective on asymmetric least squares. Journal of the American Statistical Association, 114 (527). pp. 1366-1381. ISSN 1537-274X https://www.tandfonline.com/doi/full/10.1080/01621459.2018.1498348 doi:10.1080/01621459.2018.1498348 doi:10.1080/01621459.2018.1498348
spellingShingle Stupfler, Gilles
Daouia, Abdelaati
Gijbels, Irène
Extremiles: a new perspective on asymmetric least squares
title Extremiles: a new perspective on asymmetric least squares
title_full Extremiles: a new perspective on asymmetric least squares
title_fullStr Extremiles: a new perspective on asymmetric least squares
title_full_unstemmed Extremiles: a new perspective on asymmetric least squares
title_short Extremiles: a new perspective on asymmetric least squares
title_sort extremiles: a new perspective on asymmetric least squares
url https://eprints.nottingham.ac.uk/52820/
https://eprints.nottingham.ac.uk/52820/
https://eprints.nottingham.ac.uk/52820/