Tail risk inference via expectiles in heavy-tailed time series

DOI10.1080/07350015.2022.2078332arXiv2004.04078OpenAlexW3205009003MaRDI QIDQ135350FDOQ135350

Authors: Anthony C. Davison, Simone Padoan, Gilles Stupfler, A. C. Davison, S. A. Padoan, Gilles Stupfler 

Publication date: 8 April 2020

Published in: Journal of Business and Economic Statistics (Search for Journal in Brave)

Abstract: Expectiles define the only law-invariant, coherent and elicitable risk measure apart from the expectation. The popularity of expectile-based risk measures is steadily growing and their properties have been studied for independent data, but further results are needed to use extreme expectiles with dependent time series such as financial data. In this paper we establish a basis for inference on extreme expectiles and expectile-based marginal expected shortfall in a general $$-mixing context that encompasses ARMA, ARCH and GARCH models with heavy-tailed innovations. Simulations and applications to financial returns show that the new estimators and confidence intervals greatly improve on existing ones when the data are dependent.

Full work available at URL: https://arxiv.org/abs/2004.04078

zbMATH Keywords

weak dependenceasymmetric least squares estimationmarginal expected shortfallmixingtail copula

Mathematics Subject Classification ID

Asymptotic properties of nonparametric inference (62G20) Applications of statistics to economics (62P20) Extreme value theory; extremal stochastic processes (60G70) Statistics of extreme values; tail inference (62G32)

Cites Work

• Semiparametric regression with R
• Mixing: Properties and examples
• Limit theory for the sample autocorrelations and extremes of a GARCH \((1,1)\) process.
• Coherent measures of risk
• Extreme value theory. An introduction.
• Making and evaluating point forecasts
• Asymmetric Least Squares Estimation and Testing
• Title not available (Why is that?)
• Weighted approximations of tail processes for \(\beta\)-mixing random variables.
• Generalized quantiles as risk measures
• Limit theorems for empirical processes of cluster functionals
• A simple general approach to inference about the tail of a distribution
• Extreme quantile estimation for dependent data, with applications to finance
• Adapting extreme value statistics to financial time series: dealing with bias and serial dependence
• Extreme quantile estimation for \(\beta\)-mixing time series and applications
• Extreme M-quantiles as risk measures: from \(L^{1}\) to \(L^{p}\) optimization
• Extreme conditional expectile estimation in heavy-tailed heteroscedastic regression models
• Tail expectile process and risk assessment
• Assessing value at risk with CARE, the conditional autoregressive expectile models
• MIXING PROPERTIES OF A GENERAL CLASS OF GARCH(1,1) MODELS WITHOUT MOMENT ASSUMPTIONS ON THE OBSERVED PROCESS
• Estimation of Parameters and Larger Quantiles Based on the k Largest Observations
• Estimation of Tail Risk Based on Extreme Expectiles
• New weighted portmanteau statistics for time series goodness of fit testing
• Estimation of the marginal expected shortfall: the mean when a related variable is extreme
• Stationarity and geometric ergodicity of BEKK multivariate GARCH models

Cited In (5)

• Estimation of the conditional tail moment for Weibull-type distributions
• Tail risk monotonicity in GARCH(1,1) models
• Estimation of tail risk using extreme expectiles in linear GARCH models with heavy-tailed error
• ExtremeRisks
• Inference for extremal regression with dependent heavy-tailed data

This page was built for publication: Tail risk inference via expectiles in heavy-tailed time series

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q135350)