Second-order refined peaks-over-threshold modelling for heavy-tailed distributions

DOI10.1016/J.JSPI.2009.01.006zbMATH Open1162.62044arXiv0901.1518OpenAlexW1990340489MaRDI QIDQ1022014FDOQ1022014

Johan Segers, J. Beirlant, Elisabeth Joossens

Publication date: 9 June 2009

Published in: Journal of Statistical Planning and Inference (Search for Journal in Brave)

Abstract: Modelling excesses over a high threshold using the Pareto or generalized Pareto distribution (PD/GPD) is the most popular approach in extreme value statistics. This method typically requires high thresholds in order for the (G)PD to fit well and in such a case applies only to a small upper fraction of the data. The extension of the (G)PD proposed in this paper is able to describe the excess distribution for lower thresholds in case of heavy tailed distributions. This yields a statistical model that can be fitted to a larger portion of the data. Moreover, estimates of tail parameters display stability for a larger range of thresholds. Our findings are supported by asymptotic results, simulations and a case study.

Full work available at URL: https://arxiv.org/abs/0901.1518

zbMATH Keywords

heavy tailstail probabilitybias reductionextreme value indexHill estimatorregular variationtail empirical processextended Pareto distributionWeissman probability estimator

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Asymptotic properties of nonparametric inference (62G20) Statistics of extreme values; tail inference (62G32)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• An introduction to statistical modeling of extreme values
• Asymptotic Statistics
• Statistics of Extremes
• Statistical inference using extreme order statistics
• Residual life time at great age
• Estimating tails of probability distributions
• A simple general approach to inference about the tail of a distribution
• ``Asymptotically unbiased estimators of the tail index based on external estimation of the second order parameter
• On exponential representations of log-spacings of extreme order statistics
• A dynamical mixture model for unsupervised tail estimation without threshold selection
• A new class of semi-parametric estimators of the second order parameter.
• Tail index estimation and an exponential regression model
• On maximum likelihood estimation of the extreme value index.
• Estimation of Parameters and Larger Quantiles Based on the k Largest Observations
• Estimating a tail exponent by modelling departure from a Pareto distribution
• Approximate distributions of order statistics. With applications to nonparametric statistics
• Semiparametric lower bounds for tail index estimation
• Modeling actuarial data with a composite lognormal-Pareto model
• Alternatives to a semi-parametric estimator of parameters of rare events -- the jackknife methodology
• A general class of estimators of the extreme value index
• Bias reduction and explicit semi-parametric estimation of the tail index
• Estimating the First- and Second-Order Parameters of a Heavy-Tailed Distribution
• Refined pickands estimators wtth bias correction
• Asymptotically unbiased estimators for the extreme-value index
• Generalized Pickands estimators for the extreme value index

Cited In (27)

• Conditional tail moment and reinsurance premium estimation under random right censoring
• Conditional marginal expected shortfall
• Modeling of censored bivariate extremal events
• Nonparametric estimation of conditional marginal excess moments
• Second-order tail asymptotics of deflated risks
• Robust and bias-corrected estimation of the coefficient of tail dependence
• Heavy-Tailed Density Estimation
• Robust and asymptotically unbiased estimation of extreme quantiles for heavy tailed distributions
• Robust and bias-corrected estimation of the probability of extreme failure sets
• Local robust estimation of Pareto-type tails with random right censoring
• Bias-corrected estimation for conditional Pareto-type distributions with random right censoring
• A flexible extended generalized Pareto distribution for tail estimation
• Bias reduced tail estimation for censored Pareto type distributions
• Extreme Value Theory and Statistics of Univariate Extremes: A Review
• Extreme value estimation of the conditional risk premium in reinsurance
• Dependent conditional tail expectation for extreme levels
• Bias-reduced estimators for bivariate tail modelling
• Robust estimation of Pareto-type tail index through an exponential regression model
• Local robust and asymptotically unbiased estimation of conditional Pareto-type tails
• Robust estimation of the conditional stable tail dependence function
• Hunting for Black Swans in the European Banking Sector Using Extreme Value Analysis
• Bias-corrected and robust estimation of the bivariate stable tail dependence function
• Penalized bias reduction in extreme value estimation for censored Pareto-type data, and long-tailed insurance applications
• Robust nonparametric estimation of the conditional tail dependence coefficient
• Tail fitting for truncated and non-truncated Pareto-type distributions
• On \(1/f\) noise
• Title not available (Why is that?)

Uses Software

• ismev

This page was built for publication: Second-order refined peaks-over-threshold modelling for heavy-tailed distributions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1022014)