Distribution of the largest root of a matrix for Roy's test in multivariate analysis of variance

DOI10.1016/J.JMVA.2015.10.007zbMATH Open1327.62329arXiv1401.3987OpenAlexW1847041450MaRDI QIDQ900830FDOQ900830

Marco Chiani

Publication date: 23 December 2015

Published in: Journal of Multivariate Analysis (Search for Journal in Brave)

Abstract: Let $$ denote two independent real Gaussian $mathsfpimesmathsfm$ and $mathsfpimesmathsfn$ matrices with $mathsfm,mathsfngeqmathsfp$, each constituted by zero mean i.i.d. columns with common covariance. The Roy's largest root criterion, used in multivariate analysis of variance (MANOVA), is based on the statistic of the largest eigenvalue, $Thet{a}_1$, of $$, where $$ and $$ are independent central Wishart matrices. We derive a new expression and efficient recursive formulas for the exact distribution of $Thet{a}_1$. The expression can be easily calculated even for large parameters, eliminating the need of pre-calculated tables for the application of the Roy's test.

Full work available at URL: https://arxiv.org/abs/1401.3987

Recommendations

• Numerical computation for the exact distribution of Roy's largest root statistic under linear alternative
• Exact distributional computations for Roy's statistic and the largest eigenvalue of a Wishart distribution
• Roy's largest root test under rank-one alternatives
• Percentage points of the largest characteristic root of the multivariate beta matrix
• Approximation of the power functions of Roy's largest root test under general spiked alternatives

zbMATH Keywords

largest eigenvaluerandom matricescharacteristic rootsTracy-Widom distributionWishart matricesmultivariate analysis of variance (MANOVA)Roy's test

Mathematics Subject Classification ID

Multivariate distribution of statistics (62H10) Hypothesis testing in multivariate analysis (62H15) Analysis of variance and covariance (ANOVA) (62J10)

Cites Work

• Title not available (Why is that?)
• On the distribution of the largest eigenvalue in principal components analysis
• Title not available (Why is that?)
• On orthogonal and symplectic matrix ensembles
• Level-spacing distributions and the Airy kernel
• Shape fluctuations and random matrices
• Multivariate analysis and Jacobi ensembles: largest eigenvalue, Tracy-Widom limits and rates of convergence
• Approximate null distribution of the largest root in multivariate analysis
• On the capacity of spatially correlated mimo rayleigh-fading channels
• Title not available (Why is that?)
• Hypergeometric Functions of Scalar Matrix Argument are Expressible in Terms of Classical Hypergeometric Functions
• Exact distributional computations for Roy's statistic and the largest eigenvalue of a Wishart distribution
• Upper percentage points of the largest root of a matrix in multivariate analysis
• The Distributions of Random Matrix Theory and their Applications
• Distribution of the largest eigenvalue for real Wishart and Gaussian random matrices and a simple approximation for the Tracy-Widom distribution
• Distribution of the Largest or the Smallest Characteristic Root Under Null Hypothesis Concerning Complex Multivariate Normal Populations
• Charts of Some Upper Percentage Points of the Distribution of the Largest Characteristic Root

Cited In (11)

• Numerical computation for the exact distribution of Roy's largest root statistic under linear alternative
• Limiting behavior of eigenvalues in high-dimensional MANOVA via RMT
• Percentage points of the largest characteristic root of the multivariate beta matrix
• On the domain of attraction of a Tracy-Widom law with applications to testing multiple largest roots
• Roy's largest root under rank-one perturbations: the complex valued case and applications
• Computable structural formulas for the distribution of the \(\beta\)-Jacobi edge eigenvalues
• Computation of the expected Euler characteristic for the largest eigenvalue of a real non-central Wishart matrix
• On the distribution of an arbitrary subset of the eigenvalues for some finite dimensional random matrices
• Expressing the largest eigenvalue of a singular beta F-matrix with heterogeneous hypergeometric functions
• Exact and approximate computation of critical values of the largest root test in high dimension
• Testing independence under a block compound symmetry covariance structure

This page was built for publication: Distribution of the largest root of a matrix for Roy's test in multivariate analysis of variance

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q900830)