<>
I would say it is a convenience command and can be replicated interactively,
as seen in MUS, chap. 3.6.3, http://www.stata-press.com/books/mus.html,
or indeed levpredict.ado itself...
HTH
Martin
-----Ursprüngliche Nachricht-----
Von: [email protected]
[mailto:[email protected]] Im Auftrag von Shun
Chonabayashi
Gesendet: Mittwoch, 10. Juni 2009 17:03
An: [email protected]
Betreff: st: RE: AW: levpredict
Thanks for your reply. Then, is there any other way I can achieve the same
objective without using "levpredict"?
Shun
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Martin Weiss
Sent: Wednesday, June 10, 2009 10:49 AM
To: [email protected]
Subject: st: AW: levpredict
<>
A technical answer would be for you to look at its code in -levpredict.ado-
and note that it conditions via -if e(sample)- so that predictions are
calculated only for the estimation sample.
HTH
Martin
-----Ursprüngliche Nachricht-----
Von: [email protected]
[mailto:[email protected]] Im Auftrag von Shun
Chonabayashi
Gesendet: Mittwoch, 10. Juni 2009 16:29
An: [email protected]
Betreff: st: levpredict
Is "levpredict" can be used to make out-of-sample predictions? If so, could
anybody please let me know how we can do that? Thanks for your time.
Sincerely,
Shun
*
* 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/
*
* 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/
