Principal Component Analysis Under Correlated Multivariate Regression Equations Model.
Abstract
The motivation behind the study in this paper is to derive some asymptotic results useful in the area of principal component analysis under the CMRE model. The object of the principal component analysis is to select a small number of important linear combinations of the variables which will best describe the variation among experimental units. In this paper, the authors consider the problem of testing for the equality of the last few eigenvalues of the covariance matrix under correlated multivariate regression equations models. Asymptotic distributions of various test statistics are derived when the underlying distribution is multivariate normal. Some of the distribution theory is extended to the case when the underlying distribution is elliptically symmetric.
Document Details
- Document Type
- Technical Report
- Publication Date
- Apr 01, 1985
- Accession Number
- ADA160266
Entities
People
- Paruchuri R. Krishnaiah
- Suman Sarkar
Organizations
- University of Pittsburgh