The extremogram: A correlogram for extreme events

Abstract

We consider a strictly stationary sequence of random vectors whose finite-dimensional distributions are jointly regularly varying with some positive index. This class of processes includes, among others, ARMA processes with regularly varying noise, GARCH processes with normally or Student-distributed noise and stochastic volatility models with regularly varying multiplicative noise. We define an analog of the autocorrelation function, the extremogram, which depends only on the extreme values in the sequence. We also propose a natural estimator for the extremogram and study its asymptotic properties under $\alpha$-mixing. We show asymptotic normality, calculate the extremogram for various examples and consider spectral analysis related to the extremogram.

Published in at http://dx.doi.org/10.3150/09-BEJ213 the Bernoulli (http://isi.cbs.nl/bernoulli/) by the International Statistical Institute/Bernoulli Society (http://isi.cbs.nl/BS/bshome.htm)

References in corpus (1)

• The extremogram: A correlogram for extreme events

Cited by in corpus (17)

• The extremogram: A correlogram for extreme events
• A functional limit theorem for dependent sequences with infinite variance stable limits
• Quantile spectral processes: Asymptotic analysis and inference
• An exceptional max-stable process fully parameterized by its extremal coefficients
• A modeler's guide to extreme value software
• A Fourier analysis of extreme events
• Quantile Fourier Transform, Quantile Series, and Nonparametric Estimation of Quantile Spectra
• The integrated periodogram of a dependent extremal event sequence
• Asymptotic independence and support detection techniques for heavy-tailed multivariate data
• Causality in extremes of time series
• The integrated copula spectrum
• The Reactive Volatility Model
• Improved inference on risk measures for univariate extremes
• Spline Autoregression Method for Estimation of Quantile Spectrum
• Extreme Treatment Effect: Extrapolating Dose-Response Function Into Extreme Treatment Domain
• Whittle estimation based on the extremal spectral density of a heavy-tailed random field
• Quantile-Crossing Spectrum and Spline Autoregression Estimation