Vladimir Vakhitov <[email protected]> and Jeremy Page <[email protected]>:
The solution below does not give the desired result, but substitute _N
for _n and it does. Or in one:
bys id: g balanced = (_N==7)
However, observations may exist and yet contain missing values and
therefore be excluded from the regression. Thus you need something
more like
qui xtreg y x, i(id) fe
g ok=e(sample)
egen sumok=total(ok), by(id)
su sumok, meanonly
g allok=(sumok==r(max))
xtreg y x if allok==1, i(id) fe
On Fri, Mar 28, 2008 at 3:20 PM, Vladimir Vakhitov <[email protected]> wrote:
> Hi Jeremy,
>
> I would use a simple trick (ID is your panel variable):
>
> tempvar q
> bysort id: gen `q' = _n
> gen byte balanced = 0
> replace balanced = 1 if `q'==7
>
> Vladimir.
>
> 2008/3/28, Jeremy Page <[email protected]>:
> > I have an unbalanced panel of seven period and I would like to be able
> > to make a subset of a balanced panel. I have created dummy variables
> > (T1-T7) for each of the time periods as well as a continuous variable
> > labeled time (1-7). I would like to create another dummy variable to
> > use in the "if" qualifier of a regression which would be "balanced=1"
> > if there are observations in all 7 periods.
*
* 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/
