in addition, if your model is not correctly specified, you
might obtain missing values in the variance-covariance
matrix. Then these standard errors cannot be calculated,
hence, se, p and cf are missing.
Daniel
-----Ursprungliche Nachricht-----
Von: [email protected]
[mailto:[email protected]]Im Auftrag von
Nick Cox
Gesendet: Donnerstag, 21. November 2002 15:17
An: [email protected]
Betreff: st: RE: missing estimates
Henrik Andersson
>
> probably a trivial question, but I will ask it anyway
since
> I do not find
> any answer in the "manuals". Sometimes when I run a
> regression the estmates
> for std. err., t-value, p-value, and conf.int. are missing
from the
> "output". They are only market by a dot. Why is that?
Here's one circumstance. If the estimate
of the standard error is 0, then by
an obvious sequence t, P and the limits
are all indeterminate. It's perhaps arguable
that in that circumstance the se should be
shown as 0, but either way the practical
message is the same.
Nick
[email protected]
*
* 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/
