Statalist


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

RE: st: keeping likelihood for every observation


From   "Stephane Mahuteau" <smahutea@efs.mq.edu.au>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: keeping likelihood for every observation
Date   Tue, 09 Feb 2010 11:08:06 +1100

Thank you for your help.
it seems to work fine when I insert this command inside a program i actually write (same with Maarten's suggestion) but it doesn't seem to work if I just put the command in a do file where I use an already made model  contained in a separate ado file like, for example heckman or craggit etc... Some of the models I wish to estimate are a bit cumbersome and have multiple equations and I'd rather use the user written programs rather than reprogramming the whole likelihood myself. Being fairly new with stata programming it seems to be beyond my abilities at the moment. Is there any command I can run after an estimation command that would give me those estimated likelihood for every observation or should I get into the ado file for the model I am trying to estimate, locate the `lnf'=..... and insert after that: replace ml_save='lnf' ?
thank you,
Steph

 



*
*   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