On singular values of data matrices with general independent columns

DOI10.1214/23-AOS2263MaRDI QIDQ6172191zbMATH OpenFDO

Authors

Publication date 19 July 2023

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

Full work available at URL https://arxiv.org/abs/2108.06677

zbMATH Keywords

eigenvalue distributionlarge data matrixlarge sample covariance matricesmatrix-valued autoregressive modelrealized covariance matrixseparable covariance matrixsingular value distribution

Mathematics Subject Classification ID

Random matrices (probabilistic aspects) (60B20) Multivariate distribution of statistics (62H10)

Abstract: In this paper, we analyse singular values of a large $pimesn$ data matrix $mathbf{X}_n=(mathbf{x}_{n1},ldots,mathbf{x}_{nn})$ where the column $mathbf{x}_{nj}$'s are independent $p$-dimensional vectors, possibly with different distributions. Such data matrices are common in high-dimensional statistics. Under a key assumption that the covariance matrices $mathbf{Sigma}_{nj}=extCov(mathbf{x}_{nj})$ can be asymptotically simultaneously diagonalizable, and appropriate convergence of their spectra, we establish a limiting distribution for the singular values of $mathbf{X}_n$ when both dimension $p$ and $n$ grow to infinity in a comparable magnitude. The matrix model goes beyond and includes many existing works on different types of sample covariance matrices, including the weighted sample covariance matrix, the Gram matrix model and the sample covariance matrix of linear times series models. Furthermore, we develop two applications of our general approach. First, we obtain the existence and uniqueness of a new limiting spectral distribution of realized covariance matrices for a multi-dimensional diffusion process with anisotropic time-varying co-volatility processes. Secondly, we derive the limiting spectral distribution for singular values of the data matrix for a recent matrix-valued auto-regressive model. Finally, for a generalized finite mixture model, the limiting spectral distribution for singular values of the data matrix is obtained.

Recommendations

• On the singular value distribution of large-dimensional data matrices whose columns have different correlations
• On singular value distribution of large-dimensional autocovariance matrices
• On singular values distribution of a matrix large auto-covariance in the ultra-dimensional regime
• Moment approach for singular values distribution of a large auto-covariance matrix
• The asymptotic distribution of singular values with applications to canonical correlations and correspondence analysis

Cites work

• A note on a Marčenko-Pastur type theorem for time series
• Asymptotic error distributions for the Euler method for stochastic differential equations
• Autoregressive models for matrix-valued time series
• Constrained Factor Models for High-Dimensional Matrix-Variate Time Series
• DISTRIBUTION OF EIGENVALUES FOR SOME SETS OF RANDOM MATRICES
• Factor models for matrix-valued high-dimensional time series
• Finite mixture and Markov switching models.
• Finite mixture models
• scientific article; zbMATH DE number 5278585 (Why is no real title available?)
• scientific article; zbMATH DE number 5691097 (Why is no real title available?)
• Large sample covariance matrices and high-dimensional data analysis
• Limiting spectral distribution of a symmetrized auto-cross covariance matrix
• Limiting spectral distribution of large-dimensional sample covariance matrices generated by VARMA
• On Structure Testing for Component Covariance Matrices of a High Dimensional Mixture
• On the empirical distribution of eigenvalues of a class of large dimensional random matrices
• On the estimation of integrated covariance matrices of high dimensional diffusion processes
• On the limiting empirical measure of eigenvalues of the sum of rank one matrices with log-concave distribution
• On the Marčenko-Pastur law for linear time series
• Random matrix theory in statistics: a review
• Spectral analysis of large dimensional random matrices
• Strong convergence of the empirical distribution of eigenvalues of large dimensional random matrices
• The Distribution of Realized Exchange Rate Volatility
• The empirical distribution of the eigenvalues of a Gram matrix with a given variance profile
• Toeplitz and circulant matrices: a review.

Cited in

(1)

• A CLT for the difference of eigenvalue statistics of sample covariance matrices

This page was built for publication: On singular values of data matrices with general independent columns

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6172191)