Re: st: confirmatory factor analysis with binary variables

[Steven Samuels <sjhsamuels@earthlink.net>]

On Dec 12, 2008, at 3:55 PM, Buckley, Gillian J. wrote:
> I am trying to do a confirmatory factor analysis on data that is  
> all binary, 0=no, 1=yes.   I have downloaded the tertrachoric  
> command and used this to find the tertrachoric correlations.  Is it  
> possible to do confirmatory factor analysis with this data using  
> the cfa1 command in Stata 9?


The Statalist FAQ state: "Say what command(s) you are using. If they  
are not part of official Stata, say where they come from: the STB/SJ,  
SSC, or other archives."

 -cfa1- (and its more able sibling -cfa-) were written by Stas  
Kolenikov. The -help- files (available online if you type "search  
cfa1, all")  show no provision for inputting correlation matrices.

-gllamm-  ("search gllamm, all") will fit CFAs, but people more  
experienced than I report that this is not easy.  Also, -gllamm- will  
not report standard CFA fit statistics.

Look into Mike Neale's free MX Program, which is available for a  
variety of platforms.  I learned about it from Jay Verkuilen's post  
at http://www.stata.com/statalist/archive/2008-11/msg00776.html

-Steve
*
*   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/