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]
Re: st: xtmelogit
From
"JVerkuilen (Gmail)" <[email protected]>
To
[email protected]
Subject
Re: st: xtmelogit
Date
Wed, 14 Nov 2012 10:31:18 -0500
On Wed, Nov 14, 2012 at 10:13 AM, Nick Cox <[email protected]> wrote:
> Depending on one's background and target audience it is often good
> advice to start with a less complex model and try to make it simpler!
Yes, I made this point to the students, too. The example I use for
teaching is the venerable 22 beta-blocker studies meta-analysis
(Yusuf, et. al) that appears in several sources, which can be written
as a mixed logistic regression with random intercept (for different
study base rates of death) and random slope (for study effect
heterogeneity). You can fit this in class quite nicely showing
different layouts of the data (individual, grouped binomial, etc.) and
fit them in real time so they can see how things go.
Yusuf, S, Peto, R., Lewis, J., Collins, R., & Sleight, P. (1985). Beta
blockade during and after myocardial infarction: an overview of the
randomized trials. Progress in Cardiovascular Disease, 27, 335-371.
For many purposes clustered robust standard errors does just as well
as the more complex mixed model.
Jay
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/