Separation theorems for singular values of matrices and their applications in multivariate analysis

Journal of Multivariate Analysis

Volumn 9, Issue 3, 1979, Pages 362-377

  Rao, C Radhakrishna ^a,b  

^a UNIVERSITY OF PITTSBURGH   (United States)

^b INDIAN STATISTICAL INSTITUTE   (India)

Author keywords

canonical correlations; estimation of residuals; Matrix approximations; multivariate linear regression; unitarily invariant norm

Indexed keywords

EID: 0002407065     PISSN: 0047259X     EISSN: 10957243     Source Type: Journal    
DOI: 10.1016/0047-259X(79)90094-0     Document Type: Article

References (17)

1. Optimality properties of Theil's BLUS residuals
2. Reduced rank regression for the multivariate linear model
3. The minimal transformation to orthonormality
4. Maximum properties and inequalities for the eigenvalues of completely continuous operators
5. Some metric inequalities in the space of matrices
6. Symmetric gauge functions and unitarily invariant norms
7. Abrahamse and Koerts' “new estimator” of disturbances in regression analysis
8. Optimality of principal components
9. Minimization of eigenvalues of a matrix and optimality of principal components
10. The use and interpretation of principal components in applied research
11. Matrix approximations and reduction of dimensionality in multivariate statistical analysis
12. Notes on a matrix approximation problem and some related matrix inequalities
13. The analysis of disturbances in regression analysis
14. An extremum property of sums of eigenvalues
15. Some matrix inequalities and metrization of matric spaces