webuse nlswork
tsset idcode year
xtdes // is the panel unbalanced?
xtreg grade ln_wage, fe // anything..
gen sample=e(sample)
tab sample // how many OBS are dropped
tab idcode if sample==1 // what groups are not dropped (0 for the dropped)
Basically, the idea is to use the e(sample) function (which u can use
after xtreg, see ereturn list). Afterwards, you just use a tab.
I hope that helps,
Sergio
On 11/13/06, Pavlos C. Symeou <[email protected]> wrote:
Dear Statalisters,
I am running a FE model for a complete set of 214 countries for 25 years.
The regression results indicate that only 140 countries (groups) are used in
the estimation, a result of STATA omitting incomplete data rows. Is there a
way I can see which countries are included in the estimation? This is
important to make useful conclusions.
Yours,
Pavlos
*
* 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/
*
* 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/
