--- On Tue, 11/8/09, Xu, Haiyong wrote:
> I got an error message which I don't understand when I was
> testing the Cronbach's alpha of the factors' scores after
> doing factor analysis to a few variables.
<snip>
> . factor pcs3 mcs3 sfindex3 eurq2 depress_score1_rev, pcf
<snip>
> . predict factor1 factor2
<snip>
> . alpha factor1 factor2, std item detail
> variable __00000P not found
> r(111);
I agree that this is not an informative error message, and that
that should be fixed. My intuition says that it doesn't make
sense to compute a Cronbach's alpha on factor scores rather than
the original variables, but I will happily bow to superior
wisdom, which I am sure exists in abundance in this case.
One such source of superior wisdom that you have close at hand
are the good people of ATS:
http://www.ats.ucla.edu/stat/Schedule/walk_in.htm
We at the list will happily help you, but you just can't beat
a face to face discussion.
Hope this helps,
Maarten
-----------------------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany
http://home.fsw.vu.nl/m.buis/
-----------------------------------------
*
* 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/
