I suspect that you could benefit
from a pseudo-time variable,
numbering first, second, ...
observations for each person 1, 2, ...
and then -tsset-ting using that.
Also exclude all missings.
Nick
[email protected]
Katsuhide Isa
> Thank you for your further comment.
>
> > -tsset- should work fine with panel
> > data. Looking again at the example
> > data you showed previously, I see
> > that you do not have data for each
> > year. However, the error message
> > below arises for a different reason.
> >
> > Try
> >
> > . duplicates list code year
>
> You are right.
> -duplicates- detected not a few duplicated observations.
> When I retried after deleting those observations, thing went well.
>
> Though I'm not still sure how to utilize -tsspell- to create
> a variable
> that records the number of distinct values in -dept- for each sample,
> I give it time and keep trying.
>
*
* 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/
