Abstract
Fisher matrix is one of the most important statistics in multivariate statistical analysis. Its eigenvalues are of primary importance for many applications, such as testing the equality of mean vectors, testing the equality of covariance matrices and signal detection problems. In this paper, we establish the limiting spectral distribution of high-dimensional noncentral Fisher matrices and investigate its analytic behavior. In particular, we show the determination criterion for the support of the limiting spectral distribution of the noncentral Fisher matrices, which is the base of investigating the high-dimensional problems concerned with noncentral Fisher matrices.
Similar content being viewed by others
References
Anderson T. An Introduction to Multivariate Statistical Analysis, 3rd ed. New York: Wiley, 2003
Bai Z D, Ding X. Estimation of spiked eigenvalues in spiked models. Random Matrices Theory Appl, 2012, 1: 1150011
Bai Z D, Silverstein J W. No eigenvalues outside the support of the limiting spectral distribution of information-plus-noise type matrices. Random Matrices Theory Appl, 2012, 1: 1150004
Banna M, Najim J, Yao J F. A CLT for linear spectral statistics of large random information-plus-noise matrices. Stochastic Process Appl, 2020, 130: 2250–2281
Bao Z G, Hu J, Pan G M, et al. Canonical correlation coefficients of high-dimensional Gaussian vectors: Finite rank case. Ann Statist, 2019, 47: 612–640
Bodnar T, Dette H, Parolya N. Testing for independence of large dimensional vectors. Ann Statist, 2019, 47: 2977–3008
Capitaine M. Exact separation phenomenon for the eigenvalues of large information-plus-noise type matrices, and an application to spiked models. Indiana Univ Math J, 2014, 63: 1875–1910
Dozier R B, Silverstein J W. On the empirical distribution of eigenvalues of large dimensional information-plus-noise-type matrices. J Multivariate Anal, 2007, 98: 678–694
Dozier R B, Silverstein J W. Analysis of the limiting spectral distribution of large dimensional information-plus-noise type matrices. J Multivariate Anal, 2007, 98: 1099–1122
Han X, Pan G M, Zhang B. The Tracy-Widom law for the largest eigenvalue of F type matrices. Ann Statist, 2016, 44: 1564–1592
James A T. Distributions of matrix variates and latent roots derived from normal samples. Ann Math Statist, 1964, 35: 475–501
Johnstone I M, Nadler B. Roy’s largest root test under rank-one alternatives. Biometrika, 2017, 104: 181–193
Li W M, Chen J Q, Qin Y L, et al. Estimation of the population spectral distribution from a large dimensional sample covariance matrix. J Statist Plann Inference, 2013, 143: 1887–1897
Ma Z M, Yang F. Sample canonical correlation coefficients of high-dimensional random vectors with finite rank correlations. arXiv:2102.03297, 2021
Muirhead R J. Aspects of Multivariate Statistical Theory. Hoboken: John Wiley & Sons, 1982
Silverstein J W, Choi S I. Analysis of the limiting spectral distribution of large dimensional random matrices. J Multivariate Anal, 1995, 54: 295–309
Yang F. Limiting distribution of the sample canonical correlation coefficients of high-dimensional random vectors. Electron J Probab, 2022, 27: 86
Yang F. Sample canonical correlation coefficients of high-dimensional random vectors: Local law and Tracy-Widom limit. Random Matrices Theory Appl, 2022, 11: 2250007
Zhang Z X, Pan G M. Tracy-Widom law for the extreme eigenvalues of large signal-plus-noise matrices. arXiv: 2009.12031, 2020
Zheng S R. Central limit theorems for linear spectral statistics of large dimensional F-matrices. Ann Inst Henri Poincaré Probab Stat, 2012, 48: 444–476
Zheng S R, Bai Z D, Yao J F. Substitution principle for CLT of linear spectral statistics of high-dimensional sample covariance matrices with applications to hypothesis testing. Ann Statist, 2015, 43: 546–591
Zheng S R, Bai Z D, Yao J F. CLT for linear spectral statistics of a rescaled sample precision matrix. Random Matrices Theory Appl, 2015, 4: 1550014
Zheng S R, Bai Z D, Yao J F. CLT for eigenvalue statistics of large-dimensional general Fisher matrices with applications. Bernoulli, 2017, 23: 1130–1178
Acknowledgements
Zhidong Bai was supported by National Natural Science Foundation of China (Grant No. 12171198). Jiang Hu was supported by National Natural Science Foundation of China (Grant Nos. 12171078 and 11971097) and National Key R&D Program of China (Grant No. 2020YFA0714102). We thank the two reviewers for careful reading of the manuscript and their helpful comments that improve this paper.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zhang, X., Bai, Z. & Hu, J. Limiting spectral distribution of high-dimensional noncentral Fisher matrices and its analysis. Sci. China Math. 66, 393–408 (2023). https://doi.org/10.1007/s11425-020-1958-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11425-020-1958-1