Indices, heuristics and strategies to help determine the number of factors/components to retain:
- Acceleration factor (noc with or without Parallel Analysis)
- Optimal Coordinates (noc with or without Parallel Analysis)
- Parallel analysis (components, factors and bootstrap)
- \(\lambda >= \bar{\lambda}\) (Kaiser, CFA and related rule)
- Cattell-Nelson-Gorsuch (CNG)
- Zoski and Jurs Multiple regression (\(\beta\), t and p)
- Zoski and Jurs standard error of the regression coefficient (sescree, \(S_{Y \bullet X}\))
- Nelson \(R^2\)
- Bartlett \(\chi^2\)
- Anderson \(\chi^2\)
- Lawley \(\chi^2\) and
- Bentler-Yuan \(\chi^2\).
| Package: | nFactors |
| Type: | Package |
| Version: | 2.3.2 |
| Date: | 2010-04-10 |
| Depends: | R (>= 2.9.2), MASS, psych, boot |
| License: | GPL |
Raiche, G., Riopel, M. and Blais, J.-G. (2006). Non graphical solutions for the Cattell's scree test. Paper presented at the International Annual meeting of the Psychometric Society, Montreal. [http://www.er.uqam.ca/nobel/r17165/RECHERCHE/COMMUNICATIONS/]
Other packages are also very useful for principal component and factor analysis. The R psychometric view is instructive at this point. See http://cran.stat.sfu.ca/web/views/Psychometrics.html for further details.