Universality results for the largest eigenvalues of some sample covariance matrix ensembles

For sample covariance matrices with i.i.d. entries with sub-Gaussian tails, when both the number of samples and the number of variables become large and the ratio approaches one, it is a well-known result of Soshnikov that the limiting distribution of the largest eigenvalue is same that of Gaussian samples. In this paper, we extend this result to two cases. The first case is when the ratio approaches an arbitrary finite value. The second case is when the ratio becomes infinite or arbitrarily small.     

A note on the largest eigenvalue of a large dimensional sample covariance matrix

Let {v_ij; i, J = 1, 2, …} be a family of i.i.d. random variables with E(v₁₁⁴) = ∞. For positive integers p, n with p = p(n) and p/n → y > 0 as n → ∞, let M_n = (1/n) V_n V_n^T , where V_n = (v_ij)_{1 ≤ i ≤ p, 1 ≤ j ≤ n}, and let λ_max(n) denote the largest eigenvalue of M_n. It is shown that a.s. This result verifies the boundedness of E(v₁₁⁴) to be the weakest condition known to assure the almost sure convergence of λ_max(n) for a class of sample covariance matrices.     

On the limit of the largest eigenvalue of the large dimensional sample covariance matrix

Summary In this paper the authors show that the largest eigenvalue of the sample covariance matrix tends to a limit under certain conditions when both the number of variables and the sample size tend to infinity. The above result is proved under the mild restriction that the fourth moment of the elements of the sample sums of squares and cross products (SP) matrix exist.Research sponsored by the Air Force Office of Scientific Research under Contract F49620-C-0008. The United States Government is authorized to reproduce and distribute reprints for governmental purposes notwithstanding any copyright notation hereonThe work of this author was done when he was working at the Center for Multivariate Analysis, University of Pittsburgh.     

A matrix derivation of the asymptotic covariance matrix of sample correlation coefficients

The asymptotic covariance matrix of the sample correlation matrix is derived in matrix form as an application of some new matrix theory in multivariate statistics.     

Asymptotic theory for maximum deviations of sample covariance matrix estimates

We consider asymptotic distributions of maximum deviations of sample covariance matrices, a fundamental problem in high-dimensional inference of covariances. Under mild dependence conditions on the entries of the data matrices, we establish the Gumbel convergence of the maximum deviations. Our result substantially generalizes earlier ones where the entries are assumed to be independent and identically distributed, and it provides a theoretical foundation for high-dimensional simultaneous inference of covariances.     

Eigenvalues of large sample covariance matrices of spiked population models

We consider a spiked population model, proposed by Johnstone, in which all the population eigenvalues are one except for a few fixed eigenvalues. The question is to determine how the sample eigenvalues depend on the non-unit population ones when both sample size and population size become large. This paper completely determines the almost sure limits of the sample eigenvalues in a spiked model for a general class of samples.     

Interpretations of some parameter dependent generalizations of classical matrix ensembles

Two types of parameter dependent generalizations of classical matrix ensembles are defined by their probability density functions (PDFs). As the parameter is varied, one interpolates between the eigenvalue PDF for the superposition of two classical ensembles with orthogonal symmetry and the eigenvalue PDF for a single classical ensemble with unitary symmetry, while the other interpolates between a classical ensemble with orthogonal symmetry and a classical ensemble with symplectic symmetry. We give interpretations of these PDFs in terms of probabilities associated to the continuous Robinson-Schensted-Knuth correspondence between matrices, with entries chosen from certain exponential distributions, and non-intersecting lattice paths, and in the course of this probability measures on partitions and pairs of partitions are identified. The latter are generalized by using Macdonald polynomial theory, and a particular continuum limit – the Jacobi limit – of the resulting measures is shown to give PDFs related to those appearing in the work of Anderson on the Selberg integral, and also in some classical work of Dixon. By interpreting Andersons and Dixons work as giving the PDF for the zeros of a certain rational function, it is then possible to identify random matrices whose eigenvalue PDFs realize the original parameter dependent PDFs. This line of theory allows sampling of the original parameter dependent PDFs, their Dixon-Anderson-type generalizations and associated marginal distributions, from the zeros of certain polynomials defined in terms of random three term recurrences.Supported by the Australian Research Council     

Some limit theorems for the eigenvalues of a sample covariance matrix

Limit theorems are given for the eigenvalues of a sample covariance matrix when the dimension of the matrix as well as the sample size tend to infinity. The limit of the cumulative distribution function of the eigenvalues is determined by use of a method of moments. The proof is mainly combinatorial. By a variant of the method of moments it is shown that the sum of the eigenvalues, raised to k-th power, k = 1, 2,…, m is asymptotically normal. A limit theorem for the log sum of the eigenvalues is completed with estimates of expected value and variance and with bounds of Berry-Esseen type.     

The asymptotic covariance matrix of sample correlation coefficients under general conditions

A general matrix expression for the asymptotic covariance matrix of correlation coefficients is derived. It is applicable when the data are drawn from any distribution with finite fourth order moments. The result is specialized to the cases where the data have a distribution from the elliptical class and where the sample covariance matrix has a noncentral Wishart distribution.     

Convergence of empirical spectral distributions of large dimensional quaternion sample covariance matrices

In this paper, we establish the limit of empirical spectral distributions of quaternion sample covariance matrices. Motivated by Bai and Silverstein (Spectral analysis of large dimensional random matrices, Springer, New York, 2010) and Mar?enko and Pastur (Matematicheskii Sb, 114:507–536, 1967), we can extend the results of the real or complex sample covariance matrix to the quaternion case. Suppose \(\mathbf X_n = ({x_{jk}^{(n)}})_{p\times n}\) is a quaternion random matrix. For each \(n\), the entries \(\{x_{ij}^{(n)}\}\) are independent random quaternion variables with a common mean \(\mu \) and variance \(\sigma ^2>0\). It is shown that the empirical spectral distribution of the quaternion sample covariance matrix \(\mathbf S_n=n^{-1}\mathbf X_n\mathbf X_n^*\) converges to the Mar?enko–Pastur law as \(p\rightarrow \infty \), \(n\rightarrow \infty \) and \(p/n\rightarrow y\in (0,+\infty )\).     

Some limit theorems on the eigenvectors of large dimensional sample covariance matrices

Let {v_ij} i,j = 1, 2,…, be i.i.d. standardized random variables. For each n, let V_n = (v_ij) i = 1, 2,…, n; j = 1, 2,…, s = s(n), where $\text{(}\text{n}\text{s}\text{) → y > 0}$ as n → ∞, and let $\text{M}{}_{\mathrm{n}}\text{= (}\text{1}\text{s}\text{)V}{}_{\mathrm{n}}\text{V}{}_{\mathrm{n}}{}^{\mathrm{T}}$. Previous results [7, 8] have shown the eigenvectors of M_n to display behavior, for n large, similar to those of the corresponding Wishart matrix. A certain stochastic process X_n on [0, 1], constructed from the eigenvectors of M_n, is known to converge weakly, as n → ∞, on D[0, 1] to Brownian bridge when v₁₁ is N(0, 1), but it is not known whether this property holds for any other distribution. The present paper provides evidence that this property may hold in the non-Wishart case in the form of limit theorems on the convergence in distribution of random variables constructed from integrating analytic function w.r.t. X_n(F_n(x)), where F_n is the empirical distribution function of the eigenvalues of M_n. The theorems assume certain conditions on the moments of v₁₁ including E(v₁₁⁴) = 3, the latter being necessary for the theorems to hold.     

On testing sphericity and identity of a covariance matrix with large dimensions

Tests for certain covariance structures, including sphericity, are presented when the data may be high-dimensional but not necessarily normal. The tests are formulated as functions of location-invariant estimators defined as U-statistics of higher order kernels. Under a few mild assumptions, the limit distributions of the tests are shown to be normal. The accuracy of the tests is demonstrated by simulations.     

The limiting spectral distribution function of large dimensional random matrices of sample covariance type

Results on the analytic behavior of the limiting spectral distribution of matrices of sample covariance type, studied in Marcěnko and Pastur [2], are derived. Using the Stieltjes transform, it is shown that the limiting distrbution has a continuous derivative away from zero, the derivative being analytic whenever it is positive, and the behavior of it resembles the behavior of a square root function near the boundary of its support.     

Asymptotic distributions of functions of the eigenvalues of sample covariance matrix and canonical correlation matrix in multivariate time series

Let S = (1/n) Σ_t=1ⁿ X(t) X(t)′, where X(1), …, X(n) are p × 1 random vectors with mean zero. When X(t) (t = 1, …, n) are independently and identically distributed (i.i.d.) as multivariate normal with mean vector 0 and covariance matrix Σ, many authors have investigated the asymptotic expansions for the distributions of various functions of the eigenvalues of S. In this paper, we will extend the above results to the case when {X(t)} is a Gaussian stationary process. Also we shall derive the asymptotic expansions for certain functions of the sample canonical correlations in multivariate time series. Applications of some of the results in signal processing are also discussed.     

Spectra of infinite-dimensional sample covariance matrices

We study spectral functions of infinite-dimensional random Gram matrices of the form RR^T, where R is a rectangular matrix with an infinite number of rows and with the number of columns N → ∞, and the spectral functions of infinite sample covariance matrices calculated for samples of volume N → ∞ under conditions analogous to the Kolmogorov asymptotic conditions. We assume that the traces d of the expectations of these matrices increase with the number N such that the ratio d/N tends to a constant. We find the limiting nonlinear equations relating the spectral functions of random and nonrandom matrices and establish the asymptotic expression for the resolvent of random matrices. __________ Translated from Teoreticheskaya i Matematicheskaya Fizika, Vol. 148, No. 2, pp. 309–322, August, 2006.     

A new method for the estimation of variance components directly from the sample covariance matrix

Statistical techniques for the estimation of variance components are usually associated with methodological and computational difficulties. In this paper a new computational method for the estimation of variance components directly from the sample covariance matrix is proposed. A comparison between this method and the maximum likelihood method for variance component estimation, based on their computational performance, is made. Cases for balanced and unbalanced simulated data assuming a two-way nixed model with correlated errors are considered, and a real-life application in animal breeding is presented.     

Strong convergence of the empirical distribution of eigenvalues of sample covariance matrices with a perturbation matrix

Let , where is a random symmetric matrix, a random symmetric matrix, and with being independent real random variables. Suppose that , and are independent. It is proved that the empirical spectral distribution of the eigenvalues of random symmetric matrices converges almost surely to a non-random distribution.