论文信息 - Principal Components and Regression by Singular Value Decomposition on a Small Computer

Principal Components and Regression by Singular Value Decomposition on a Small Computer

A compact program for performing a variety of regression and principal component computations is described. A singular value decomposition of the data matrix is used which permits calculations involving rank deficient data to be handled satisfactorily. The importance of avoiding the calculation of a sum of squares and cross‐products matrix is demonstrated by an example.

J. C. Nash | J. Nash | L. Lefkovitch | L. P. Lefkovitch

[1] G. Golub,et al. Numerical computations for univariate linear models , 1973 .

[2] S. Hammarling. A Note on Modifications to the Givens Plane Rotation , 1974 .

[3] Donald W. Marquaridt. Generalized Inverses, Ridge Regression, Biased Linear Estimation, and Nonlinear Estimation , 1970 .

[4] G. Stewart. Introduction to matrix computations , 1973 .

[5] J. Gower. Some distance properties of latent root and vector methods used in multivariate analysis , 1966 .

[6] J. Putter,et al. Orthonormal Bases of Error Spaces and Their Use for Investigating the Normality and Variances of Residuals , 1967 .

[7] James Hardy Wilkinson,et al. The Least Squares Problem and Pseudo-Inverses , 1970, Comput. J..

[8] John C. Nash,et al. A One-Sided Transformation Method for the Singular Value Decomposition and Algebraic Eigenproblem , 1975, Comput. J..

[9] G. Golub. MATRIX DECOMPOSITIONS AND STATISTICAL CALCULATIONS , 1969 .

[10] W. E. Gentleman. Least Squares Computations by Givens Transformations Without Square Roots , 1973 .

[11] Richard J. Hanson. Stably updating mean and standard deviation of data , 1975, CACM.