|
|  |
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: suest for ologit
Olvar Bergland <[email protected]> is having trouble using -suest- after
-ologit-:
> I am testing differences in coefficients across several ologit models.
>
> When using suest and STATA v 9.2 I get the following error message:
> “Score variables for model X contain missing values”
>
> This did indeed work for with STATA version 8.2, but as I was revisiting the
> analysis my old batch program crashed/stopped. Changing the command from
> ologit to oprobit did not produce any error messages.
>
> Searching the stata-list Bart Vanneste suggested regarding a similiar problem
> for "suest for intreg":
>
> >suest requires the predict, score option to give non-missing values,
> >so I guess that’s where it goes wrong.
>
> Any solutions to work around it? (For other reasons I want to keep the logit
> formulation.)
Olvar's original do-file should not have any problems provided it has a proper
-version- statement at the top. If Olvar's do-file was written while using
Stata 8.2, the first line of the do-file should be
version 8.2
Olvar can email me directly if the above -version- statement does not fix the
problem.
--Jeff
[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/
