Factor loadings optimally account for the non-diagonal elements of the covariance matrix of observed variables. Principal component analysis leads to components accounting for a maximum of the variance of the observed variables. Retained-components factor transformation is proposed in order to combine the advantages of factor analysis and principal component analysis.
Beauducel, André and Spohn, Frank
"Retained-Components Factor Transformation: Factor Loadings and Factor Score Predictors in the Column Space of Retained Components,"
Journal of Modern Applied Statistical Methods:
2, Article 6.
Available at: http://digitalcommons.wayne.edu/jmasm/vol13/iss2/6