Summary
In this paper, we consider the distribution of the maximum latent root of a certain positive definite symmetric random matrix. For this purpose, we give a useful transformation of a symmetric matrix and calculate its Jacobian. We also give some useful expansion formulas for zonal polynomials (A. T. James [3]).
Recently Sugiyama [7] and Sugiyama and Hukutomi [8] gave the density functions of maximum latent roots of a central Wishart matrix when the covariance matrix Σ=I, and of a multivariate Beta matrix and a multivariateF-matrix in the central case.
Here we derive the density functions of maximum latent roots of a multivariate non-central Beta matrix, a non-central Wishart matrix and a multivariate central quadratic form with the covariance matrix Σ, and we also derive the density function of maximum canonical correlation coefficient. The notations in this paper are due to A. T. James [4] and A. G. Constantine [1].
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
A. G. Constantine, “Some non-central distribution problems in multivariate analysis,”Ann. Math. Statist., 34 (1963), 1270–1285.
A. G. Constantine, “The distribution of Hotelling's generalizedT 20 ,”Ann. Math. Statist., 37 (1966), 215–225.
A. T. James, “Zonal polynomials of the real positive definite symmetric matrices,”Ann. of Math., 74 (1961), 456–469.
A. T. James, “Distribution of matrix variates and latent roots derived from normal samples,”Ann. Math. Statist., 35 (1964), 475–501.
Y. Tumura, “The distributions of latent roots and vectors,”Tokyo Rika Univ. Math., 1 (1965), 1–16.
T. Hayakawa, “On the distribution of a quadratic form in a multivariate normal sample,”Ann. Inst. Statist. Math., 18 (1966), 191–201.
T. Sugiyama, “On the distribution of the largest latent root and the corresponding latent vector for principal component analysis,”Ann. Math. Statist., 37 (1966), 995–1001.
T. Sugiyama and K. Hukutomi, “Note on the distribution of the maximum (minimum) characteristic root in multivariate analysis,” The abstract presented at the meeting of Japan Mathematical Society, Oct., 1966.
W. L. Deemer and I. Olkin, “The Jacobian of certain matrix transformations useful in multivariate analysis,”Biometrika, 38 (1951), 345–367.
Author information
Authors and Affiliations
About this article
Cite this article
Hayakawa, T. On the distribution of the maximum latent root of a positive definite symmetric random matrix. Ann Inst Stat Math 19, 1–17 (1967). https://doi.org/10.1007/BF02911665
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02911665