Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: AW: predict bug?


From   "Martin Weiss" <martin.weiss1@gmx.de>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: AW: predict bug?
Date   Mon, 8 Jun 2009 17:40:14 +0200

<> 

Can you give an example using datasets shipped with Stata? Otherwise it
should be a case for tech support...



HTH
Martin


-----Ursprüngliche Nachricht-----
Von: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] Im Auftrag von Stefan Kreisel
Gesendet: Montag, 8. Juni 2009 17:37
An: statalist@hsphsun2.harvard.edu
Betreff: st: predict bug?

Hi all.
When calculating a model with "ologit" (same bug? with "oprobit" or
"regress" for that matter) with many independent categorical variables (25
in all; model has >2500 observations) and then using "predict yhat, xb" I
get a bunch of cases (not all) with predictions=0; when calculating the
linear predictor by hand, the results are perfectly identical to the stata
output of the other non-zero predictions and the cases where stata predicted
a 0, all calculate to non-zero numbers. Any ideas?
Regards!
Stefan Kreisel

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index