[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

From |
"Verkuilen, Jay" <JVerkuilen@gc.cuny.edu> |

To |
"'statalist@hsphsun2.harvard.edu'" <statalist@hsphsun2.harvard.edu> |

Subject |
st: RE: PCA vs. Factor Loadings |

Date |
Wed, 16 Dec 2009 12:00:34 -0500 |

Michael I. Lichter wrote: >>Hello. Why are component loadings from -pca- so much smaller than factor loadings from -factor-? Is there something about the procedure used by Stata that makes them systematically smaller? I get the sense (which may be mistaken; I don't have any evidence in my hand) that in other packages -pca- and -factor- loadings are more similar.<< As Nick already pointed out, the normalization you choose will affect the coefficients you get. This is very much analogous to coding variables in regression. What is preserved by the procedure is the objective function's measure of discrepancy between the input matrix and the parameters. The resulting coefficients can end up looking VERY different for statistically equivalent models. (Yes, PCA isn't properly a statistical model but it's still the result of an optimization process, or could be thought of that way.) In general, comparing loadings from factor analysis and PCA is more than a bit dangerous, though it often works, roughly speaking, especially when the variables input into factor analysis have relatively small uniquenesses. JV * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/

**References**:**st: PCA vs. Factor Loadings***From:*"Michael I. Lichter" <MLichter@Buffalo.EDU>

- Prev by Date:
**RE: st: RE: AW: Creating single values from a nested data file** - Next by Date:
**Re: st: Choice of analysis time in survival analysis where the hazard is associated with age** - Previous by thread:
**RE: st: RE: PCA vs. Factor Loadings** - Next by thread:
**st: clogit, "initial values not feasible" error** - Index(es):

© Copyright 1996–2016 StataCorp LP | Terms of use | Privacy | Contact us | What's new | Site index |