Multiple block sizes and overlapping blocks for multivariate time series extremes

DOI10.1214/20-AOS1957zbMATH Open1461.62167arXiv1907.09477OpenAlexW3093380516MaRDI QIDQ2656597FDOQ2656597

Authors: Nan Zou, Stanislav Volgushev, Axel Bücher 

Publication date: 11 March 2021

Published in: The Annals of Statistics (Search for Journal in Brave)

Abstract: Block maxima methods constitute a fundamental part of the statistical toolbox in extreme value analysis. However, most of the corresponding theory is derived under the simplifying assumption that block maxima are independent observations from a genuine extreme value distribution. In practice however, block sizes are finite and observations from different blocks are dependent. Theory respecting the latter complications is not well developed, and, in the multivariate case, has only recently been established for disjoint blocks of a single block size. We show that using overlapping blocks instead of disjoint blocks leads to a uniform improvement in the asymptotic variance of the multivariate empirical distribution function of rescaled block maxima and any smooth functionals thereof (such as the empirical copula), without any sacrifice in the asymptotic bias. We further derive functional central limit theorems for multivariate empirical distribution functions and empirical copulas that are uniform in the block size parameter, which seems to be the first result of this kind for estimators based on block maxima in general. The theory allows for various aggregation schemes over multiple block sizes, leading to substantial improvements over the single block length case and opens the door to further methodology developments. In particular, we consider bias correction procedures that can improve the convergence rates of extreme-value estimators and shed some new light on estimation of the second-order parameter when the main purpose is bias correction.

Full work available at URL: https://arxiv.org/abs/1907.09477

Recommendations

• Extreme value copula estimation based on block maxima of a multivariate stationary time series
• Inference for heavy tailed stationary time series based on sliding blocks
• Weak convergence of a pseudo maximum likelihood estimator for the extremal index
• Maximum likelihood estimators based on the block maxima method
• Asymptotics for sliding blocks estimators of rare events

zbMATH Keywords

extreme-value copulaempirical processblock maximamixing coefficientsbias correctionsecond-order condition

Mathematics Subject Classification ID

Asymptotic properties of nonparametric inference (62G20) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Large deviations (60F10) Extreme value theory; extremal stochastic processes (60G70) Asymptotic distribution theory in statistics (62E20) Statistics of extreme values; tail inference (62G32) Characterization and structure theory for multivariate probability distributions; copulas (62H05) Estimation in multivariate analysis (62H12)

Cites Work

• Weak convergence and empirical processes. With applications to statistics
• Modelling pairwise dependence of maxima in space
• Title not available (Why is that?)
• A nonparametric estimation procedure for bivariate extreme value copulas
• Asymptotics of empirical copula processes under non-restrictive smoothness assumptions
• Nonparametric estimation of multivariate extreme-value copulas
• Statistics of Extremes
• Extreme value theory. An introduction.
• Rank-based inference for bivariate extreme-value copulas
• An efficient semiparametric maxima estimator of the extremal index
• Weak convergence of a pseudo maximum likelihood estimator for the extremal index
• Asymptotically distribution-free goodness-of-fit testing for tail copulas
• Title not available (Why is that?)
• Title not available (Why is that?)
• Tails of multivariate Archimedean copulas
• A sliding blocks estimator for the extremal index
• Bias correction in multivariate extremes
• Extreme value copula estimation based on block maxima of a multivariate stationary time series
• Bias-corrected estimation of stable tail dependence function
• On the covariance of the asymptotic empirical copula process
• Limit theorems for empirical processes of cluster functionals
• Adapting extreme value statistics to financial time series: dealing with bias and serial dependence
• How to make a Hill plot.
• Title not available (Why is that?)
• Max-infinite divisibility
• Non-parametric Estimation of Tail Dependence
• Extreme value theory for multivariate stationary sequences
• Limit theory for multivariate sample extremes
• On the block maxima method in extreme value theory: PWM estimators
• Title not available (Why is that?)
• Multivariate extreme values in stationary random sequences
• Statistics of Heteroscedastic Extremes
• Existence and consistency of the maximum likelihood estimators for the extreme value index within the block maxima framework
• Maximum likelihood estimation for the Fréchet distribution based on block maxima extracted from a time series
• Inference for heavy tailed stationary time series based on sliding blocks
• Maximum likelihood estimators based on the block maxima method
• On second order conditions in the multivariate block maxima and peak over threshold method

Cited In (12)

• Causal discovery in heavy-tailed models
• Asymptotics for sliding blocks estimators of rare events
• Estimation of cluster functionals for regularly varying time series: runs estimators
• Limit theorems for non-degenerate U-statistics of block maxima for time series
• Statistical analysis for stationary time series at extreme levels: new estimators for the limiting cluster size distribution
• Independent block identification in multivariate time series
• On the disjoint and sliding block maxima method for piecewise stationary time series
• Estimation of cluster functionals for regularly varying time series: sliding blocks estimators
• Modelling sub-daily precipitation extremes with the blended generalised extreme value distribution
• Reweighted madogram-type estimator of Pickands dependence function
• A horse race between the block maxima method and the peak-over-threshold approach
• Estimating POT second-order parameter for bias correction

This page was built for publication: Multiple block sizes and overlapping blocks for multivariate time series extremes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2656597)