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: 2-part random effects GLM


From   Jeph Herrin <stata@spandrel.net>
To   statalist@hsphsun2.harvard.edu
Subject   st: 2-part random effects GLM
Date   Mon, 07 Jan 2013 13:47:11 -0500


All,

I am interested in estimating a 2-part random effects GLM model. I'm new to 2-part models, and unfortunately "2-part" is an ambigious search term, so none of the usual search tools have been helpful. However, I did find the package -tpm- on SSC which estimates a 2-part GLM model, but before I start trying to see what I can infer from the source code that might extend to say -gllamm-, I thought I would ask the list if anyone else has information, or even a better search term, for 2-part random effects GLM models.

Some additional context might be helpful. My particular situation is that an economist colleague handed me a paper:

 Liu, Lei & Strawderman, Robert L. & Cowen, Mark E. & Shih, Ya-Chen T.,
 2010. "A flexible two-part random effects model for correlated medical
 costs," Journal of Health Economics, Elsevier, vol. 29(1), pages
 110-123, January.
 ( http://ideas.repec.org/a/eee/jhecon/v29y2010i1p110-123.html )

and pointed out it was just the thing for a problem we'd been working on. The paper includes SAS code using NLMIXED (wherein I discovered that NLMIXED allows one to write one's own likelihood function) - and what I'm trying to avoid is moving this project to SAS for want of a model.

In sum - is there a better (more specific) name for 2-part models, or any implementation in Stata other than the -tpm- package?

thanks,
Jeph

*
*   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/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index