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: estimating profile log-likelihood limits for blogit


From   "Sheena Sullivan" <[email protected]>
To   <[email protected]>
Subject   st: estimating profile log-likelihood limits for blogit
Date   Tue, 2 Nov 2010 21:24:52 -0700

Hi all, 
I'm trying to get profile likelihood limits for a logistic regression on
grouped data.  For ungrouped data I can use the logprof command. 
For example, if I run 

. logit Y X, or
. logprof X, or

My estimate and limits from logit are: 20.6 (2.4,172.2)
While profile log-likelihood limits from logprof are: 20.6 (1.1, 119.6)
Which concurs with results I've obtained in other software.

But the logprof function can't be extended to grouped data.  So, I'm
wondering if anyone knows of a suitable function?

I found pllf but it's not clear to me whether this function can do the same
thing as logprof because it requires specification of the profile or a
formula.  If pllf can indeed do the same thing as logprof, I'm unsure how to
specify the profile or formula to get the same results.  Can anyone help?

Thanks in advance, 
Sheena Sullivan


*
*   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