Estimation of tail risk based on extreme expectiles

We use tail expectiles to estimate alternative measures to the Value at Risk (VaR) and Marginal Expected Shortfall (MES), two instruments of risk protection of utmost importance in actuarial science and statistical _nance. The concept of expectiles is a least squares analogue of quantiles. Both are...

Full description

Bibliographic Details
Main Authors: Daouia, Abdelaati, Girard, Stéphane, Stupfler, Gilles
Format: Article
Published: Wiley 2017
Subjects:
Online Access:https://eprints.nottingham.ac.uk/44962/
_version_ 1848797039245131776
author Daouia, Abdelaati
Girard, Stéphane
Stupfler, Gilles
author_facet Daouia, Abdelaati
Girard, Stéphane
Stupfler, Gilles
author_sort Daouia, Abdelaati
building Nottingham Research Data Repository
collection Online Access
description We use tail expectiles to estimate alternative measures to the Value at Risk (VaR) and Marginal Expected Shortfall (MES), two instruments of risk protection of utmost importance in actuarial science and statistical _nance. The concept of expectiles is a least squares analogue of quantiles. Both are M-quantiles as the minimizers of an asymmetric convex loss function, but expectiles are the only M-quantiles that are coherent risk measures. Moreover, expectiles de_ne the only coherent risk measure that is also elicitable. The estimation of expectiles has not, however, received any attention yet from the perspective of extreme values. Two estimation methods are proposed here, either making use of quantiles or relying directly on least asymmetrically weighted squares. A main tool is to _rst estimate large values of expectile-based VaR and MES located within the range of the data, and then to extrapolate the obtained estimates to the very far tails. We establish the limit distributions of both of the resulting intermediate and extreme estimators. We show via a detailed simulation study the good performance of the procedures, and present concrete applications to medical insurance data and three large US investment banks.
first_indexed 2025-11-14T19:57:32Z
format Article
id nottingham-44962
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T19:57:32Z
publishDate 2017
publisher Wiley
recordtype eprints
repository_type Digital Repository
spelling nottingham-449622020-05-04T19:12:03Z https://eprints.nottingham.ac.uk/44962/ Estimation of tail risk based on extreme expectiles Daouia, Abdelaati Girard, Stéphane Stupfler, Gilles We use tail expectiles to estimate alternative measures to the Value at Risk (VaR) and Marginal Expected Shortfall (MES), two instruments of risk protection of utmost importance in actuarial science and statistical _nance. The concept of expectiles is a least squares analogue of quantiles. Both are M-quantiles as the minimizers of an asymmetric convex loss function, but expectiles are the only M-quantiles that are coherent risk measures. Moreover, expectiles de_ne the only coherent risk measure that is also elicitable. The estimation of expectiles has not, however, received any attention yet from the perspective of extreme values. Two estimation methods are proposed here, either making use of quantiles or relying directly on least asymmetrically weighted squares. A main tool is to _rst estimate large values of expectile-based VaR and MES located within the range of the data, and then to extrapolate the obtained estimates to the very far tails. We establish the limit distributions of both of the resulting intermediate and extreme estimators. We show via a detailed simulation study the good performance of the procedures, and present concrete applications to medical insurance data and three large US investment banks. Wiley 2017-10-10 Article PeerReviewed Daouia, Abdelaati, Girard, Stéphane and Stupfler, Gilles (2017) Estimation of tail risk based on extreme expectiles. Journal of the Royal Statistical Society: Series B, 80 (2). pp. 263-292. ISSN 1467-9868 Asymmetric squared loss; Coherency; Expectiles; Extrapolation; Extreme values; Heavy tails; Marginal expected shortfall; Value at Risk http://onlinelibrary.wiley.com/doi/10.1111/rssb.12254/full doi:10.1111/rssb.12254 doi:10.1111/rssb.12254
spellingShingle Asymmetric squared loss; Coherency; Expectiles; Extrapolation; Extreme values; Heavy tails; Marginal expected shortfall; Value at Risk
Daouia, Abdelaati
Girard, Stéphane
Stupfler, Gilles
Estimation of tail risk based on extreme expectiles
title Estimation of tail risk based on extreme expectiles
title_full Estimation of tail risk based on extreme expectiles
title_fullStr Estimation of tail risk based on extreme expectiles
title_full_unstemmed Estimation of tail risk based on extreme expectiles
title_short Estimation of tail risk based on extreme expectiles
title_sort estimation of tail risk based on extreme expectiles
topic Asymmetric squared loss; Coherency; Expectiles; Extrapolation; Extreme values; Heavy tails; Marginal expected shortfall; Value at Risk
url https://eprints.nottingham.ac.uk/44962/
https://eprints.nottingham.ac.uk/44962/
https://eprints.nottingham.ac.uk/44962/