Score predictor factor analysis: Reproducing observed covariances by means of factor score predictors

TL;DR

This paper introduces Score predictor factor analysis, a new method that estimates factor loadings to better reproduce observed covariances using factor score predictors, outperforming traditional methods.

Contribution

It proposes a novel estimation technique for factor loadings that optimally reproduces non-diagonal covariance elements via factor score predictors.

Findings

Score predictor factor analysis more accurately reproduces covariance matrix elements.

It outperforms Minres factor analysis and principal component analysis in simulations.

Helpful for factor identification when the model fit is imperfect.

Abstract

The model implied by factor score predictors does not reproduce the non-diagonal elements of the observed covariance matrix as well as the factor loadings. It is therefore investigated whether it is possible to estimate factor loadings for which the model implied by the factor score predictors optimally reproduces the non-diagonal elements of the observed covariance matrix. Accordingly, loading estimates are proposed for which the model implied by the factor score predictors allows for a least-squares approximation of the non-diagonal elements of the observed covariance matrix. This estimation method is termed Score predictor factor analysis and algebraically compared with Minres factor analysis as well as principal component analysis. A population based and a sample based simulation study was performed in order to compare Score predictor factor analysis, Minres factor analysis, and principal component analysis. It turns out that the non-diagonal elements of the observed covariance matrix can more exactly be reproduced from the factor score predictors computed from Score predictor factor analysis than from the factor score predictors computed from Minres factor analysis and from principal components. Moreover, Score predictor factor analysis can be helpful to identify factors when the factor model does not perfectly fit to the data because of model error.