On Jun 4, 2004, at 7:33 AM, Clive wrote:
With apologies for the messy output. Kit Baum may be able to shed more
light on what the "minor modifications" are for -dwstat2- when he has
time
to reply.
CLive has said 'tsset id' with obs number (_n) as id. If these are
really panel data, this statistic
is utter rubbish. You can't lie about tsset and get any sensible
results.
If you should be saying 'tsset unit year', then dwstat will refuse to
run at all, even if you say 'dwstat if unit==1'. dwstat2 will run that
command, but will not run without the qualification. But neither
command will prevent you from computing an utterly meaningless
statistic (please see my earlier post).
Kit
*
* 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/
