Resources for Computing and Evaluating Factor Scores
This web site offers a number of resources for computing and evaluating factor scores in the context of an exploratory factor analysis. The information herein is presented in a relatively nontechnical fashion and is directed primarily toward researchers and practitioners. Specific details regarding many of the ideas herein can be found in Grice (2001), a recent special issue of Multivariate Behavioral Research, or in one of many excellent articles published on factor scores.
Information Regarding Factor Scores
SAS IML Programs for Computing and Evaluating Factor Score Estimates.
These programs are reported and described in: Grice, J. W. (2001). Computing and evaluating factor scores. Psychological Methods, 6, 430-450. (Raw Data and Correlation Matrix reported in this manuscript).Evaluating Refined (Exact) Factor Scores
Computing Coarse (Inexact) Factor Scores, based on...
- Thurstone's Regression (Equation 5): Maximizes multiple R-square. {example} {annotated output}
- ten Berge et al. (Equation 8): Correlation Preserving. {example} {annotated output}
- Bartlett (Equation 9): Univocal for orthogonal factors.
- "Idealized Variables" (Equation 10): Univocal for orthogonal factors.
Evaluating Coarse Factor ScoresThurstone's Regression (Equation 5). {example} {annotated output} ten Berge et al. (Equation 8). Bartlett (Equation 9). "Idealized Variables" (Equation 10) Program for evaluating composite factor scores. {example} {annotated output}
Methods and Formulas for Computing Factor Scores Factor Score Indeterminacy Factor Score Indeterminacy: Extensive Commentary in Multivariate Behavioral Research (Vol. 31, 1996) Manuscripts Comparing or Discussing Different Methods of Computing Factor Scores
* If you are aware of a relevant reference that is not listed, please send it to me and I will add it.
Complete Tables of Results (in .pdf format) from: Grice, J. W. (2001). A comparison of factor scores under conditions of factor obliquity. Psychological Methods, 6, 67-83.