Approximation of high quantiles from intermediate quantiles

DOI10.1007/S10687-016-0255-3zbMATH Open1349.60085arXiv1307.6501OpenAlexW1535416341WikidataQ59461570 ScholiaQ59461570MaRDI QIDQ347150FDOQ347150

Authors: Cees de Valk 

Publication date: 30 November 2016

Published in: Extremes (Search for Journal in Brave)

Abstract: Motivated by applications requiring quantile estimates for very small probabilities of exceedance, this article addresses estimation of high quantiles for probabilities bounded by powers of sample size with exponents below -1. As regularity assumption, an alternative to the Generalised Pareto tail limit is explored for this purpose. Motivation for the alternative regularity assumption is provided, and it is shown to be equivalent to a limit relation for the logarithm of survival function, the log-GW tail limit, which generalises the GW (Generalised Weibull) tail limit, a generalisation of the Weibull tail limit. The domain of attraction is described, and convergence results are presented for quantile approximation and for a simple quantile estimator based on the log-GW tail. Simulations are presented, and advantages and limitations of log-GW-based estimation of high quantiles are indicated.

Full work available at URL: https://arxiv.org/abs/1307.6501

Recommendations

• High quantiles of heavy-tailed distributions: Their estimation
• On the relative approximation error of the generalized Pareto approximation for a high quantile
• On the estimation of high quantiles
• Scaling of high-quantile estimators
• Estimating Extreme Quantiles of Weibull Tail Distributions

zbMATH Keywords

extreme value theoryhigh quantilequantile estimationextended regular variationgeneralised Weibull tail limitlog-GW tail limitWeibull tail limit

Mathematics Subject Classification ID

Extreme value theory; extremal stochastic processes (60G70) Statistics of extreme values; tail inference (62G32) Rate of growth of functions, orders of infinity, slowly varying functions (26A12) Monotonic functions, generalizations (26A48)

Cites Work

• Extreme value theory. An introduction.
• Statistical inference using extreme order statistics
• Extreme quantile estimation for dependent data, with applications to finance
• Bias correction in extreme value statistics with index around zero
• Title not available (Why is that?)
• Estimation of Parameters and Larger Quantiles Based on the k Largest Observations
• Title not available (Why is that?)
• A moment estimator for the index of an extreme-value distribution
• Bias-reduced estimators of the Weibull tail-coefficient
• On the estimation of the Weibull tail coefficient
• Title not available (Why is that?)
• Comparison of Weibull tail-coefficient estimators
• Weibull tail-distributions revisited: A new look at some tail estimators
• Bias reduction for high quantiles
• Strong limit theorems for weighted quantile processes
• On the estimation of high quantiles
• Slowly varying functions and asymptotic relations
• Fighting the arch–enemy with mathematics‘

Cited In (12)

• Q-convergence with interquartile ranges
• On the estimation of high quantiles
• Linking representations for multivariate extremes via a limit set
• On tests to distinguish distribution tails invariant with respect to the scale parameter
• Samples with a limit shape, multivariate extremes, and risk
• On dealing with the unknown population minimum in parametric inference
• Approximation and estimation of very small probabilities of multivariate extreme events
• On the relative approximation error of the generalized Pareto approximation for a high quantile
• Robust estimation and regression with parametric quantile functions
• Asymptotic behavior of the extrapolation error associated with the estimation of extreme quantiles
• Parametric estimation of non-crossing quantile functions
• Estimation of conditional extreme risk measures from heavy-tailed elliptical random vectors

This page was built for publication: Approximation of high quantiles from intermediate quantiles

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q347150)