Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


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

st: xtivreg2, hierarchical regressions, log likelihood question


From   Ari Dothan <[email protected]>
To   [email protected]
Subject   st: xtivreg2, hierarchical regressions, log likelihood question
Date   Wed, 9 May 2012 09:28:30 +0300

Dear all,
When doing hierarchical regressions in xtivreg2, I keep the endogenous
variable and all the excluded instruments in the equation, and
gradually add the included instruments.
Rather than declining from the log likelihood values obtained with the
base model (controls only) with the addition of the included
instruments, it grows in most cases, showing higher values of
(negative) log likelihood.
I believe that this is unusual, but I look for an expert opinion of
whether this is this in line with the equation structure, and why.
Thanking you very much


-- 
Ari Dothan
*
*   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index