<>
You may want to look at
http://www.stata.com/statalist/archive/2009-08/msg00321.html where
longitudinal data are mentioned...
HTH
Martin
-----Ursprüngliche Nachricht-----
Von: [email protected]
[mailto:[email protected]] Im Auftrag von Thomas Klausch
Gesendet: Freitag, 9. Oktober 2009 17:29
An: [email protected]
Betreff: st: An alternative for -micombine- to use MI data with -xtlogit-
Dear stata listeners,
Some days ago I posted the request below. I mean to bring it back to
your attention hoping that sb. might know a good response. Thanks.
I am imputing missing data using MI as provided by -ice-. As I
understand -micombine- helps receiving combined estimates for various
regression models. I actually intended to model a dichotomous variable
from a panel with random effects logistic/probit regression. However
-xtlogit- seems not to be provided as supported regression command in
-micombine-. My question is whether I can use the results of MI
somehow with this model or if it is just not implemented yet and in
that case, if there is an alternative command/way.
Thank you very much.
Thomas
*
* 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/
*
* 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/
