Almost sure convergence of the largest and smallest eigenvalues of high-dimensional sample correlation matrices

Abstract

In this paper, we show that the largest and smallest eigenvalues of a sample correlation matrix stemming from $n$ independent observations of a $p$-dimensional time series with iid components converge almost surely to $(1+\sqrt{\gamma }{)}^2$ and $(1-\sqrt{\gamma }{)}^2$, respectively, as $n\to \infty$, if $p/n\to \gamma \in (0,1]$ and the truncated variance of the entry distribution is 'almost slowly varying', a condition we describe via moment properties of self-normalized sums. Moreover, the empirical spectral distributions of these sample correlation matrices converge weakly, with probability 1, to the Marchenko-Pastur law, which extends a result in Bai and Zhou (2008). We compare the behavior of the eigenvalues of the sample covariance and sample correlation matrices and argue that the latter seems more robust, in particular in the case of infinite fourth moment. We briefly address some practical issues for the estimation of extreme eigenvalues in a simulation study. In our proofs we use the method of moments combined with a Path-Shortening Algorithm, which efficiently uses the structure of sample correlation matrices, to calculate precise bounds for matrix norms. We believe that this new approach could be of further use in random matrix theory.

arXiv commentStochastic Process. Appl. 128 (2018), no. 8, 2779-2815

References in corpus (10)

• Quantitative estimates of the convergence of the empirical covariance matrix in Log-concave Ensembles
• Distribution functions for largest eigenvalues and their applications
• Concentration of measure and spectra of random matrices: Applications to correlation matrices, elliptical distributions and beyond
• Covariance estimation for distributions with $2+\epsilon$ moments
• Fractal Weyl Law for Open Chaotic Maps
• Efficient Computation of Limit Spectra of Sample Covariance Matrices
• Poisson Statistics for the Largest Eigenvalues in Random Matrix Ensemble
• Extreme value analysis for the sample autocovariance matrices of heavy-tailed multivariate time series
• The bootstrap, covariance matrices and PCA in moderate and high-dimensions
• The eigenvalues of the sample covariance matrix of a multivariate heavy-tailed stochastic volatility model

Cited by in corpus (5)

• A Rigorous Theory of Conditional Mean Embeddings
• The asymptotic distribution of the condition number for random circulant matrices
• Limiting distributions for eigenvalues of sample correlation matrices from heavy-tailed populations
• Extreme singular values of inhomogeneous sparse random rectangular matrices
• Coherence of high-dimensional random matrices in a Gaussian case : application of the Chen-Stein method