Estimation and uncertainty quantification for extreme quantile regions

DOI10.1007/S10687-019-00364-0zbMATH Open1466.62291arXiv1904.08251OpenAlexW2995616440WikidataQ126563628 ScholiaQ126563628MaRDI QIDQ73765FDOQ73765

Boris Beranger, Scott A. Sisson, S. A. Sisson, Boris Beranger, S. A. Padoan

Publication date: 16 December 2019

Published in: Extremes (Search for Journal in Brave)

Abstract: Estimation of extreme quantile regions, spaces in which future extreme events can occur with a given low probability, even beyond the range of the observed data, is an important task in the analysis of extremes. Existing methods to estimate such regions are available, but do not provide any measures of estimation uncertainty. We develop univariate and bivariate schemes for estimating extreme quantile regions under the Bayesian paradigm that outperforms existing approaches and provides natural measures of quantile region estimate uncertainty. We examine the method's performance in controlled simulation studies. We illustrate the applicability of the proposed method by analysing high bivariate quantiles for pairs of pollutants, conditionally on different temperature gradations, recorded in Milan, Italy.

Full work available at URL: https://arxiv.org/abs/1904.08251

Recommendations

• Erratum to: ``Estimation and uncertainty quantification for extreme quantile regions
• Estimating extreme bivariate quantile regions
• Estimation of extreme conditional quantiles
• Estimation of extreme depth-based quantile regions
• Accounting for the threshold uncertainity in extreme value estimation
• Estimation of upper quantiles under model and parameter uncertainty.
• A review of extreme value threshold estimation and uncertainty quantification
• Algorithmic Learning Theory
• On optimizing the estimation of extreme value quantiles of probability distributions

zbMATH Keywords

air pollutionBayesian nonparametricsBernstein polynomialsextremal dependenceextreme quantile regionsmax-stable distributions

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Large deviations (60F10) Statistics of extreme values; tail inference (62G32) Estimation in multivariate analysis (62H12) Applications of statistics to environmental and related topics (62P12)

Cites Work

• Bayesian inference for the extremal dependence
• Extreme Dependence Models
• A nonparametric method for producing isolines of bivariate exceedance probabilities
• Weak convergence and optimal scaling of random walk Metropolis algorithms
• Generalized Pareto copulas: a key to multivariate extremes
• Estimating extreme bivariate quantile regions
• Modelling dependence uncertainty in the extremes of Markov chain
• Likelihood estimators for multivariate extremes
• Posterior propriety in Bayesian extreme value analyses using reference priors
• Adaptive optimal scaling of Metropolis–Hastings algorithms using the Robbins–Monro process
• Likelihood Inference for Multivariate Extreme Value Distributions Whose Spectral Vectors have known Conditional Distributions
• Statistics for near independence in multivariate extreme values
• Maximum likeiihood estimation of the parameters of the three-parameter generalized extreme-value distribution from censored samples
• A Conditional Approach for Multivariate Extreme Values (with Discussion)
• Statistics of Extremes
• Bayesian modeling of air pollution extremes using nested multivariate max‐stable processes
• Likelihood-Based Inference for Max-Stable Processes
• Title not available (Why is that?)
• An adaptive Metropolis algorithm
• Graphical interaction models for multivariate time series.
• Extreme value properties of multivariate \(t\) copulas
• Estimation of extreme risk regions under multivariate regular variation

Cited In (12)

• A modeler's guide to extreme value software
• Estimating extreme bivariate quantile regions
• Confidence regions for high quantiles of a heavy tailed distribution
• A review of extreme value threshold estimation and uncertainty quantification
• Extreme quantiles estimation for actuarial applications
• On dealing with the unknown population minimum in parametric inference
• Environmental contours as Voronoi cells
• Estimation of multivariate tail quantities
• ExtremalDep
• Reference Priors for the Generalized Extreme Value Distribution
• Frontier estimation and extreme value theory
• Estimation of extreme risk regions under multivariate regular variation

This page was built for publication: Estimation and uncertainty quantification for extreme quantile regions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q73765)