Large sample autocovariance matrices of linear processes with heavy tails

DOI10.1016/J.SPA.2021.07.010zbMATH Open1476.60014arXiv2001.05056OpenAlexW3188266795MaRDI QIDQ2238893FDOQ2238893

Authors: Johannes Heiny, T. Mikosch 

Publication date: 2 November 2021

Published in: Stochastic Processes and their Applications (Search for Journal in Brave)

Abstract: We provide asymptotic theory for certain functions of the sample autocovariance matrices of a high-dimensional time series with infinite fourth moment. The time series exhibits linear dependence across the coordinates and through time. Assuming that the dimension increases with the sample size, we provide theory for the eigenvectors of the sample autocovariance matrices and find explicit approximations of a simple structure, whose finite sample quality is illustrated for simulated data. We also obtain the limits of the normalized eigenvalues of functions of the sample autocovariance matrices in terms of cluster Poisson point processes. In turn, we derive the distributional limits of the largest eigenvalues and functionals acting on them. In our proofs, we use large deviation techniques for heavy-tailed processes, point process techniques motivated by extreme value theory, and related continuous mapping arguments.

Full work available at URL: https://arxiv.org/abs/2001.05056

Recommendations

• Extreme value analysis for the sample autocovariance matrices of heavy-tailed multivariate time series
• Asymptotic theory for the sample covariance matrix of a heavy-tailed multivariate time series
• Eigenvalues and eigenvectors of heavy-tailed sample covariance matrices with general growth rates: the iid case
• Limit theory for the largest eigenvalues of sample covariance matrices with heavy-tails
• Eigenvalue distribution of large sample covariance matrices of linear processes

zbMATH Keywords

large deviationsregular variationlargest eigenvaluessample autocovariance matrixpoint process convergencelinearly dependent entries

Mathematics Subject Classification ID

Large deviations (60F10) Point processes (e.g., Poisson, Cox, Hawkes processes) (60G55) Extreme value theory; extremal stochastic processes (60G70) Random matrices (probabilistic aspects) (60B20) Central limit and other weak theorems (60F05) Stationary stochastic processes (60G10)

Cites Work

• Efficient computation of limit spectra of sample covariance matrices
• Time series: theory and methods.
• Factor modeling for high-dimensional time series: inference for the number of factors
• Spectral analysis of large dimensional random matrices
• On the distribution of the largest eigenvalue in principal components analysis
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Heavy-Tail Phenomena
• On the Marčenko-Pastur law for linear time series
• Limiting spectral distribution of a symmetrized auto-cross covariance matrix
• Random covariance matrices: universality of local statistics of eigenvalues
• On the limiting spectral distribution for a large class of symmetric random matrices with correlated entries
• On singular values distribution of a matrix large auto-covariance in the ultra-dimensional regime
• Large sample covariance matrices and high-dimensional data analysis
• Poisson statistics for the largest eigenvalues of Wigner random matrices with heavy tails
• Localization and delocalization for heavy tailed band matrices
• Poisson convergence for the largest eigenvalues of heavy tailed random matrices
• Poisson Statistics for the Largest Eigenvalues in Random Matrix Ensembles
• On singular value distribution of large-dimensional autocovariance matrices
• Moment approach for singular values distribution of a large auto-covariance matrix
• Identifying the number of factors from singular values of a large sample auto-covariance matrix
• Eigenvalues and eigenvectors of heavy-tailed sample covariance matrices with general growth rates: the iid case
• Limit theory for the largest eigenvalues of sample covariance matrices with heavy-tails
• Extreme value analysis for the sample autocovariance matrices of heavy-tailed multivariate time series
• Asymptotic theory for the sample covariance matrix of a heavy-tailed multivariate time series
• Spectral analysis of sample autocovariance matrices of a class of linear time series in moderately high dimensions
• A note on the limiting spectral distribution of a symmetrized auto-cross covariance matrix
• Strong limit of the extreme eigenvalues of a symmetrized auto-cross covariance matrix
• High-dimensional sample covariance matrices with Curie-Weiss entries
• Almost sure convergence of the largest and smallest eigenvalues of high-dimensional sample correlation matrices
• Extreme eigenvalue statistics of \(m\)-dependent heavy-tailed matrices

Cited In (16)

• Limiting spectral distribution of sample autocovariance matrices
• Higher order approximations for autocovariances from linear processes with applications
• Eigenvalues and eigenvectors of heavy-tailed sample covariance matrices with general growth rates: the iid case
• Limit theory for the largest eigenvalues of sample covariance matrices with heavy-tails
• Sample covariance matrix for random vectors with heavy tails
• Sample Covariance Matrices of Heavy-Tailed Distributions
• The eigenvalues of the sample covariance matrix of a multivariate heavy-tailed stochastic volatility model
• The eigenstructure of the sample covariance matrices of high-dimensional stochastic volatility models with heavy tails
• Estimation of autocovariance matrices for high dimensional linear processes
• Asymptotic behavior of eigenvalues of variance-covariance matrix of a high-dimensional heavy-tailed Lévy process
• Large covariance and autocovariance matrices
• The asymptotic distribution of the condition number for random circulant matrices
• Limiting distributions for eigenvalues of sample correlation matrices from heavy-tailed populations
• Moment bounds for large autocovariance matrices under dependence
• Extreme value analysis for the sample autocovariance matrices of heavy-tailed multivariate time series
• Asymptotic theory for the sample covariance matrix of a heavy-tailed multivariate time series

Uses Software

• SPECTRODE

This page was built for publication: Large sample autocovariance matrices of linear processes with heavy tails

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2238893)