Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


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

Re: st: Factor Analysis: which explained variance?


From   Alan Acock <acock@mac.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Factor Analysis: which explained variance?
Date   Fri, 19 Mar 2010 09:25:36 -0700

Stata offers pca and factor, pcf. It's been noted that many people use principal component analysis with rotations in scale development. I think what they are often using is SPSS factor analysis that defaults to what Stata does with factor, pcf and not pca. If I'm wrong on this, I would like a clarification since pca and factor, pcf are producing very different results. 

I strongly agree with the point that it doesn't make much sense to do factor, pcf, then a varimax rotation only to combine items from what have been estimated to be orthogonal dimensions. It seems to me if you have groups of items that are unrelated to each other than to say they are measuring a single dimension is a mistake. I still see people doing this, however.

Alan Acock
acock@mac.com



On Dec 21, 2009, at 6:26 AM, Francesco Burchi wrote:

> polychoric Var1 Var2 Var3 Var4
> matrix R = r(R)
> factormat R, n(6926) ipf   factor(1)          
> rotate, horst blanks(.3) 
> predict FACTORROTATE

*
*   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index