Best Linear Composites with a Specified Structure

1 September 1969

journal article
research article
Published by Cambridge University Press (CUP) in Psychometrika

Vol. 34 (3) , 301-318
https://doi.org/10.1007/bf02289359

Abstract

Least squares linear composites of predictors for estimating several criteria are derived, satisfying the restriction that the composites have an arbitrary specified intercorrelation matrix. These composites are compared with the usual unrestricted regression composites. An illustrative example is provided. The derivation depends on a general result, given in an appendix, about best-fitting orthonormal transformations.

Keywords

This publication has 18 references indexed in Scilit:

FACTOR TRANSFORMATION METHODS
British Journal of Statistical Psychology, 1964
On a Theorem Stated by Eckart and Young
Psychometrika, 1963
Univocal or Orthogonal Estimators of Orthogonal Factors
Psychometrika, 1963
On the Least-Squares Orthogonalization of an Oblique Transformation
Psychometrika, 1962
Optimal Estimates of Multiple Criteria with Restrictions on the Covariance Matrix of Estimated Criteria
Psychological Reports, 1960
The Orthogonal Approximation of an Oblique Structure in Factor Analysis
Psychometrika, 1952
THE INFLUENCE OF DIFFERENTIAL WEIGHTING
British Journal of Statistical Psychology, 1950
Theory of mental tests.
Published by American Psychological Association (APA) ,1950
Approaches to Univocal Factor Scores
Psychometrika, 1948
The approximation of one matrix by another of lower rank
Psychometrika, 1936