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: testing nested logistic model using mi estimate: prefix command
From
Alan Acock <[email protected]>
To
[email protected]
Subject
st: testing nested logistic model using mi estimate: prefix command
Date
Tue, 01 Nov 2011 21:11:17 -0700
I have imputed 10 complete datasets using mi. I run mi estimate: logistic pair male time_m bmi on a model. I run a second model using mi estimate: logistic pair male time_m bmi compete efficacy.
I want to test if the second model does better than the first. Since there is no log likelihood reported I don't know how to calculate a likelihood ratio chi-square test.
How can I compare these models if the log likelihood was not available with the mi estimate command prefix. I could use the lrtest or calculate it by hand using listwise/casewise deletion.
Alan Acock
[email protected]
*
* 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/