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: meglm
Alfonso Sanchez-Penalver <firstname.lastname@example.org>
Re: st: meglm
Thu, 17 Oct 2013 11:10:49 -0400
Thank you for explaining this. I will look further into the differences between glm and population averaged models.
> On Oct 17, 2013, at 10:59 AM, Clyde Schechter <email@example.com> wrote:
> Alfonso S asks:
> "...Can someone tell me if I am specifying the meglm command wrong? If
> not, why does it not reproduce the results from xtgee?"
> Apart from the fact, already pointed out by Stas Kolenikov, that
> -meglm- isn't designed for use with fractional response data, Alfonso
> should not, in any case, expect results of -meglm- to reproduce those
> from -xtgee-. The reason is that -xtgee- fits a population-averaged
> model, whereas -meglm- fits at the individual-observation level. With
> a linear model the results would be the same (up to minor differences
> resulting from different estimation methods and numerical issues).
> But for non-linear models like logit and probit, they are
> systematically different.
> Clyde Schechter
> Dept. of Family & Social Medicine
> Albert Einstein College of Medicine
> Bronx, NY, USA
> * 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/
* For searches and help try: