Multivariate analysis and Jacobi ensembles: largest eigenvalue, Tracy--Widom limits and rates of convergence

Abstract

Let $A$ and $B$ be independent, central Wishart matrices in $p$ variables with common covariance and having $m$ and $n$ degrees of freedom, respectively. The distribution of the largest eigenvalue of $(A+B{)}^{-1}B$ has numerous applications in multivariate statistics, but is difficult to calculate exactly. Suppose that $m$ and $n$ grow in proportion to $p$. We show that after centering and scaling, the distribution is approximated to second-order, $O(p^{-2/3})$, by the Tracy--Widom law. The results are obtained for both complex and then real-valued data by using methods of random matrix theory to study the largest eigenvalue of the Jacobi unitary and orthogonal ensembles. Asymptotic approximations of Jacobi polynomials near the largest zero play a central role.

Published in at http://dx.doi.org/10.1214/08-AOS605 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)

References in corpus (10)

• Level-Spacing Distributions and the Airy Kernel
• On Orthogonal and Symplectic Matrix Ensembles
• Correlation Functions, Cluster Functions and Spacing Distributions for Random Matrices
• Universality at the edge of the spectrum for unitary, orthogonal and symplectic ensembles of random matrices
• Classical skew orthogonal polynomials and random matrices
• A rate of convergence result for the largest eigenvalue of complex white Wishart matrices
• Product of random projections, Jacobi ensembles and universality problems arising from free probability
• Three routes to the exact asymptotics for the one-dimensional quantum walk
• Approximate null distribution of the largest root in multivariate analysis
• Universality for orthogonal and symplectic Laguerre-type ensembles

Cited by in corpus (39)

• A geometric analysis of subspace clustering with outliers
• Cleaning large correlation matrices: tools from random matrix theory
• Universality of covariance matrices
• Edge universality of correlation matrices
• Accuracy of the Tracy--Widom limits for the extreme eigenvalues in white Wishart matrices
• Independence test for high dimensional data based on regularized canonical correlation coefficients
• Testing for Independence of Large Dimensional Vectors
• Fast approach to the Tracy-Widom law at the edge of GOE and GUE
• Approximate null distribution of the largest root in multivariate analysis
• Minimax estimation for mixtures of Wishart distributions
• Minimax estimation in sparse canonical correlation analysis
• Distribution of the largest root of a matrix for Roy's test in multivariate analysis of variance
• Finite N corrections to the limiting distribution of the smallest eigenvalue of Wishart complex matrices
• Determining the number of factors in a forecast model by a random matrix test: cryptocurrencies
• Edge universality of separable covariance matrices
• Large deviations of the top eigenvalue of large Cauchy random matrices
• Convergence of eigenvector empirical spectral distribution of sample covariance matrices
• Limiting distribution of maximal crossing and nesting of Poissonized random matchings
• Strong Convergence of Unitary Brownian Motion
• Optimal soft edge scaling variables for the Gaussian and Laguerre even $\beta$ ensembles
• Functional form for the leading correction to the distribution of the largest eigenvalue in the GUE and LUE
• Large deviation eigenvalue density for the soft edge Laguerre and Jacobi $\beta$-ensembles
• Random Subsets of Structured Deterministic Frames have MANOVA Spectra
• Edge scaling of the β-Jacobi ensemble
• Random positive operator valued measures
• Spectral Properties of the Jacobi Ensembles via the Coulomb Gas approach
• Linear Differential Equations for the Resolvents of the Classical Matrix Ensembles
• Extreme Eigenvalue Distributions of Jacobi Ensembles: New Exact Representations, Asymptotics and Finite Size Corrections
• The Correlated Jacobi and the Correlated Cauchy-Lorentz ensembles
• Spectral Discovery of Jointly Smooth Features for Multimodal Data
• Sample canonical correlation coefficients of high-dimensional random vectors: local law and Tracy-Widom limit
• On Asymptotic Linear Convergence Rate of Iterative Hard Thresholding for Matrix Completion
• Singular values for products of two coupled random matrices: hard edge phase transition
• On Eigenvalues of the sum of two random projections
• Asymptotic expansions relating to the distribution of the length of longest increasing subsequences
• Maximum-energy records in glassy energy landscapes
• Permutation Inference for Canonical Correlation Analysis
• Matrix Denoising with Partial Noise Statistics: Optimal Singular Value Shrinkage of Spiked F-Matrices
• On the extremal eigenvalues of Jacobi ensembles at zero temperature