Limit theory for the largest eigenvalues of sample covariance matrices with heavy-tails

DOI10.1016/J.SPA.2013.07.005zbMATH Open1284.60016arXiv1108.5464OpenAlexW2169413403MaRDI QIDQ2434470FDOQ2434470

Authors: Richard A. Davis, Oliver Pfaffel, Robert Stelzer 

Publication date: 6 February 2014

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

Abstract: We study the joint limit distribution of the $k$ largest eigenvalues of a $pimesp$ sample covariance matrix $X{X}^T$ based on a large $pimesn$ matrix $X$. The rows of $X$ are given by independent copies of a linear process, $X_{it}=su{m}_j{c}_j{Z}_{i,t-j}$, with regularly varying noise $(Z_{it})$ with tail index $alphain(0,4)$. It is shown that a point process based on the eigenvalues of $X{X}^T$ converges, as $noinfty$ and $poinfty$ at a suitable rate, in distribution to a Poisson point process with an intensity measure depending on $alpha$ and $sum{c}_j^2$. This result is extended to random coefficient models where the coefficients of the linear processes $(X_{it})$ are given by $c_j(het{a}_i)$, for some ergodic sequence $(het{a}_i)$, and thus vary in each row of $X$. As a by-product of our techniques we obtain a proof of the corresponding result for matrices with iid entries in cases where $p/n$ goes to zero or infinity and $alphain(0,2)$.

Full work available at URL: https://arxiv.org/abs/1108.5464

Recommendations

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

zbMATH Keywords

random matrix theorylargest eigenvalueheavy-tailed distributionlinear processrandom coefficient modelsample covariance matrixlargest singular valuerandom matrix with dependent entries

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Point processes (e.g., Poisson, Cox, Hawkes processes) (60G55) Statistics of extreme values; tail inference (62G32) Random matrices (probabilistic aspects) (60B20)

Cites Work

• Time series: theory and methods.
• Markov Chains and Stochastic Stability
• 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?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Spectrum estimation for large dimensional covariance matrices using random matrix theory
• Title not available (Why is that?)
• Corrections to LRT on large-dimensional covariance matrix by RMT
• A note on universality of the distribution of the largest eigenvalues in certain sample covariance matrices
• Level-spacing distributions and the Airy kernel
• An introduction to random matrices
• Limit theory for moving averages of random variables with regularly varying tail probabilities
• Point process and partial sum convergence for weakly dependent random variables with infinite variance
• Limits of spiked random matrices. I
• Title not available (Why is that?)
• Asymptotic Theory for Principal Component Analysis
• Random covariance matrices: universality of local statistics of eigenvalues
• Eigenvalue distribution of large sample covariance matrices of linear processes
• A note on a Marčenko-Pastur type theorem for time series
• Title not available (Why is that?)
• Distributions of Matrix Variates and Latent Roots Derived from Normal Samples
• Statistical Theory of the Energy Levels of Complex Systems. I
• On the distribution of the roots of certain symmetric matrices
• A limit theorem for the norm of random matrices
• Universality results for the largest eigenvalues of some sample covariance matrix ensembles
• Spectrum of non-Hermitian heavy tailed random matrices
• Spectrum of large random reversible Markov chains: heavy-tailed weights on the complete graph
• Poisson convergence for the largest eigenvalues of heavy tailed random matrices
• The spectrum of heavy tailed random matrices
• Spectral measure of heavy tailed band and covariance random matrices
• Title not available (Why is that?)
• The strong limits of random matrix spectra for sample matrices of independent elements
• Strong convergence of the empirical distribution of eigenvalues of sample covariance matrices with a perturbation matrix
• Title not available (Why is that?)
• Poisson Statistics for the Largest Eigenvalues in Random Matrix Ensembles
• On the top eigenvalue of heavy-tailed random matrices

Cited In (23)

• Limit of the smallest eigenvalue of a large dimensional sample covariance matrix
• On the limit of the largest eigenvalue of the large dimensional sample covariance matrix
• Title not available (Why is that?)
• Limit Theorems for Traces of Sample Covariance Matrices
• On the weak limit of the largest eigenvalue of a large dimensional sample covariance matrix
• Eigenvalues and eigenvectors of heavy-tailed sample covariance matrices with general growth rates: the iid case
• Title not available (Why is that?)
• Almost sure convergence of the largest and smallest eigenvalues of high-dimensional sample correlation matrices
• Some strong convergence theorems for eigenvalues of general sample covariance matrices
• Random matrix theory in statistics: a review
• Extreme eigenvalues of sparse, heavy tailed random matrices
• Strong limit of the extreme eigenvalues of a symmetrized auto-cross covariance matrix
• Asymptotic behavior of eigenvalues of variance-covariance matrix of a high-dimensional heavy-tailed Lévy process
• Poisson convergence for the largest eigenvalues of heavy tailed random matrices
• Inference in Heavy-Tailed Nonstationary Multivariate Time Series
• Large sample autocovariance matrices of linear processes with heavy tails
• Random matrix theory for heavy-tailed time series
• Extreme eigenvalue statistics of \(m\)-dependent heavy-tailed matrices
• On the empirical spectral distribution for matrices with long memory and independent rows
• Limiting distributions for eigenvalues of sample correlation matrices from heavy-tailed populations
• Extreme value analysis for the sample autocovariance matrices of heavy-tailed multivariate time series
• Eigenvalues distribution limit of covariance matrices with AR processes entries
• Asymptotic theory for the sample covariance matrix of a heavy-tailed multivariate time series

This page was built for publication: Limit theory for the largest eigenvalues of sample covariance matrices with heavy-tails

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2434470)