st: Factor Analysis with Sampling Weights

[Alp Eren Yurtseven <aeren.yurtseven@tubitak.gov.tr>]

Dear Statalist contributors,

I would like to perform a two stage factor analysis on a data set with 
sampling weights. That is, in the first stage I will perform factor 
analysis on 8 groups of variables. In the second stage I will run factor 
analysis on the factor scores obtained from the previous stage. A 
similiar approach was adopted by Verspagen and Srholec 
(http://www2.druid.dk/conferences/viewpaper.php?id=2967&cf=29). pweight 
option is allowed in polychoric function, so I can feed the 
corresponding correlation matrix (with sampling weights) to factormat 
function. Similiarly means with sampling weights can also be used with 
the factormat function. I need feedback on the validity of this 
approach. I'd also appreciate if you could help me on how to properly 
incorporate standard deviations to factormat function to calculate 
factor scores. Thanks in advance.

Alp Eren Yurtseven

*
*   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/