back to first page[..][[BR]]


http://www.visualstatistics.net/Visual%20Statistics%20Multimedia/factor_analysis.htm [[BR]]
http://www.rasch.org/rmt/rmt191h.htm [[BR]]

= Kaiser criterion =
Kaiser, H. F. (1960). The application of electronic computers to factor analysis. Educational and Psychological Measurement, 20, 141-151. [[BR]]

The Kaiser criterion (Kaiser, 1960): we can retain only factors with eigenvalues greater than 1.
In essence this is like saying that, unless a factor extracts at least as much as the equivalent of one original variable, we drop it. This criterion was proposed by Kaiser (1960), and is probably the one most widely used.
{{{
pve<-100*pca.rec$eig/sum(pca.rec$eig)
round(cumsum(pve))
}}}

= Communalities =
{{{
cor(data)
library(mva)
d.pca<-princomp(data,cor=T)
d.pca
summary(d.pca)
loadings(d.pca)
d.pca$scores
d.FA <- factanal(factors = 3, covmat=cov(data))
d.FA
d.FA <- factanal(data, factors=3))
100*(1 - d.FA$uniquenesses)
}}}