Bayesian uncertainty management in temporal dependence of extremes
From MaRDI portal
Publication:508719
DOI10.1007/S10687-016-0258-0zbMATH Open1360.62246arXiv1512.01169OpenAlexW2191709989MaRDI QIDQ508719FDOQ508719
Authors: Thomas Lugrin, A. C. Davison, Jonathan A. Tawn 
Publication date: 8 February 2017
Published in: Extremes (Search for Journal in Brave)
Abstract: Both marginal and dependence features must be described when modelling the extremes of a stationary time series. There are standard approaches to marginal modelling, but long- and short-range dependence of extremes may both appear. In applications, an assumption of long-range independence often seems reasonable, but short-range dependence, i.e., the clustering of extremes, needs attention. The extremal index is a natural limiting measure of clustering, but for wide classes of dependent processes, including all stationary Gaussian processes, it cannot distinguish dependent processes from independent processes with . Eastoe and Tawn (2012) exploit methods from multivariate extremes to treat the subasymptotic extremal dependence structure of stationary time series, covering both and , through the introduction of a threshold-based extremal index. Inference for their dependence models uses an inefficient stepwise procedure that has various weaknesses and has no reliable assessment of uncertainty. We overcome these issues using a Bayesian semiparametric approach. Simulations and the analysis of a UK daily river flow time series show that the new approach provides improved efficiency for estimating properties of functionals of clusters.
Full work available at URL: https://arxiv.org/abs/1512.01169
Recommendations
extremogramextreme value theoryasymptotic independenceDirichlet processrisk analysisconditional extremesBayesian semiparametricsthreshold-based extremal index
Exact distribution theory in statistics (62E15) Bayesian inference (62F15) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Extreme value theory; extremal stochastic processes (60G70) Statistics of extreme values; tail inference (62G32) Applications of statistics to environmental and related topics (62P12)
Cites Work
- An introduction to statistical modeling of extreme values
- Exact mean integrated squared error
- Computation of multivariate normal and \(t\) probabilities
- Reversible jump Markov chain Monte Carlo computation and Bayesian model determination
- Distribution and dependence-function estimation for bivariate extreme-value distributions.
- Statistics for near independence in multivariate extreme values
- A Conditional Approach for Multivariate Extreme Values (with Discussion)
- Title not available (Why is that?)
- Extremes and related properties of random sequences and processes
- On the exceedance point process for a stationary sequence
- Likelihood estimation of the extremal index
- A Bayesian analysis of some nonparametric problems
- Title not available (Why is that?)
- Title not available (Why is that?)
- Inference for Clusters of Extreme Values
- A semiparametric estimation procedure of dependence parameters in multivariate families of distributions
- Extreme values for stationary and Markov sequences
- Extremes on river networks
- Markov chain models for threshold exceedances
- Extremes and local dependence in stationary sequences
- Automatic declustering of rare events
- Sea and wind: multivariate extremes at work
- Nonparametric estimation of the spectral measure of an extreme value distribution.
- A construction principle for multivariate extreme value distributions
- Markov chain Monte Carlo in approximate Dirichlet and beta two-parameter process hierarchical models
- Title not available (Why is that?)
- Statistical Methods for Multivariate Extremes: An Application to Structural Design
- Maximum empirical likelihood estimation of the spectral measure of an extreme-value distribu\-tion
- The pairwise beta distribution: A flexible parametric multivariate model for extremes
- Bayesian Nonparametrics
- Retrospective Markov chain Monte Carlo methods for Dirichlet process hierarchical models
- Gibbs Sampling Methods for Stick-Breaking Priors
- Heavy tailed time series with extremal independence
- Limit laws for random vectors with an extreme component
- Concepts of Independence for Proportions with a Generalization of the Dirichlet Distribution
- Diagnostics for Dependence within Time Series Extremes
- The extremogram: a correlogram for extreme events
- Conditioning on an extreme component: model consistency with regular variation on cones
- A hierarchical model for serially-dependent extremes: a study of heat waves in the western US
- Estimation of the conditional distribution of a multivariate variable given that one of its components is large: additional constraints for the Heffernan and Tawn model
- Functionals of clusters of extremes
- Modeling multiple risks: hidden domain of attraction
- Title not available (Why is that?)
- A Hierarchical Model for Extreme Wind Speeds
- Models and inference for uncertainty in extremal dependence
- Bivariate extreme statistics. II
- Modelling the distribution of the cluster maxima of exceedances of subasymptotic thresholds
- On the rate of convergence for extremes of mean square differentiable stationary normal processes
- Extreme events of Markov chains
Cited In (8)
- New estimators for the extremal index and other cluster characteristics
- A latent process model for temporal extremes
- A modeler's guide to extreme value software
- Bayesian inference for clustered extremes
- Temporal evolution of the extreme excursions of multivariate \(k\)th order Markov processes with application to oceanographic data
- \(k\)th-order Markov extremal models for assessing heatwave risks
- Editorial: Special issue on time series extremes
- Accounting for uncertainty in extremal dependence modeling using Bayesian model averaging techniques
Uses Software
This page was built for publication: Bayesian uncertainty management in temporal dependence of extremes
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q508719)
