Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | saurav pathak <sauravicbs@googlemail.com> |
| To | statalist@hsphsun2.harvard.edu |
| Subject | st: xtmixed and no of obs per group |
| Date | Tue, 23 Feb 2010 15:12:56 +0000 |
Dear All I am using a data set with 40K observations. I have 14 Independent Variables (IV) in the xtmixed command. The observations are grouped into a group variable, the number of groups are 5000. When I use *estat group *I see that the average number of observations per group is 8. My question now is whether the average number of obs = 8 which is less than the total number of IV which is 14 will have a bad effect (indeterminacy) on the estimates of xtmixed, or, is it acceptable to have such a situation where the avg no of obs per group could be less than the number of IVs Kindly help me with is Thanks Saurav * * 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/