Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Shehzad Ali <drshehzad_ali@yahoo.com> |
To | Stata List <statalist@hsphsun2.harvard.edu> |
Subject | st: xtreg and xtlogit with time-invariant variables |
Date | Sun, 28 Nov 2010 01:57:55 +0000 (GMT) |
Hi listers, I am wondering if someone could advise on this. When xtreg and xtlogit models are implemented with fixed effects option, all time-invariant variables are dropped from the analysis. I am working with a dataset with response variable observed at 3 time points. The explanatory variable includes timepoint_var (obviously varies with time) and the others are time-invariant covariates that are dropped in the analysis. Could someone advise on the best way to model the relationship between response at multiple timepoints and the time-invariant variables? I should mention that the model runs when random effects option is specified. Any help would be greatly appreciated. Many thanks, Shehzad * * 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/