Dear listers,
I am trying to analyze panel data using the xtgee
command. My initial model is as follows:
iis DDS_ID (Dentist ID)
tis time (t= 0, 1, 2, 3)
xtgee depvar gender classification, fam(gaussian)
corr(unstr)
The "time" variable corresponds to baseline, 3 months,
6 months and 12 months post introduction of
educational seminars.
The "classification" variable corresponds to the level
of education (e.g., no education, mid level education,
in depth education).
Since I expect a change in the depvar from t=0
(baseline)to the individual timepoints, should I
include the time variable in the model, in addition to
setting it in the "tis" command?. Also, how would I
test for interaction between the "classification" and
"time" if I do not include "time" in the model?
Thanks for any help.
Mike
Michael Gregory Schmader, M.S.
Graduate Student
__________________________________________________
Do you Yahoo!?
Yahoo! Web Hosting - Let the expert host your site
http://webhosting.yahoo.com
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
