Dear Anders,
thanks a log again for Your new hint and for the reference of the previous
thread about the Gini coefficient.
Kind Regards,
Carlo
-----Messaggio originale-----
Da: Anders Alexandersson [mailto:[email protected]]
Inviato: luned� 16 aprile 2007 21.46
A: Carlo Lazzaro
Oggetto: Re: R: st: No entries found for search on "r(322)"
I'm guessing that you want a permutation test of -ttest-, rather than
of -summarize- or a bootstrap of -ttest-; see a recent similar thread
for the Gini coefficient at
http://www.stata.com/statalist/archive/2007-04/msg00403.html.
Anders Alexandersson
[email protected]
Carlo Lazzaro <[email protected]> wrote:
> r(t) was a scalar of the result of a previous t-test: I was trying to
> detect and compare the change in p-values after resampling via both
> non-parametric bootstrap and Monte Carlo permutation test; in the latter
> the above mentioned error code came alive.
to my reply:
> [P] error states: "322. something that should be true of your
> estimation results is not". It would be nice to have online
> documentation for all error codes. In your example, at least Stata
> indicated that the problem is with r(t), which you used as the
> statistics to be retrieved after -summarize-. Is r(t) a typo, as I
> guess?
to Carlo's original posting:
> > after a mistaken permutation test, I have come across the r(322) error
> > message, but I found no entries for search on it.
> >
> > Any idea about that?
> >
> > permute Kappa r(t), reps(10000) verbose saving(C:\Documents and
> > Settings\carlo\Documenti\Desga\Desgaperm1
> > > 6Apr.dta, every(1) replace) seed(999) : summarize var1 var2
> > (running summarize on estimation sample)
> > 'r(t)' evaluated to missing in full sample
> > r(322);
> > No entries found for search on "r(322)"
*
* 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/
