DID YOU KNOW? DTIC has over 3.5 million final reports on DoD funded research, development, test, and evaluation activities available to our registered users. Click HERE
to register or log in.
On Limiting Empirical Distribution Function of the Eigenvalues of a Multivariate F Matrix. Revised.
PITTSBURGH UNIV PA CENTER FOR MULTIVARIATE ANALYSIS
Pagination or Media Count:
In this paper, the authors derived an explicit expression for the limit of the empirical distribution function e.d.f. of a central multivariate F matrix when the number of variables and degrees of freedom both tend to infinity in certain fashion. The authors also extended the above result to the case when the underlying distribution is not necessarily multivariate normal but the first four moments exist. The limiting distribution is useful in deriving the limiting distributions of certain test statistics which arise in multivariate analysis of variance, canonical correlation analysis and tests for the equality of two covariance matrices. Additional keywords Wishart matrices computations correlation. Author.
APPROVED FOR PUBLIC RELEASE