Statalist The Stata Listserver


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: question about SE when running _metan_ w/ random effects


From   "Erick Turner" <turnere@ohsu.edu>
To   statalist@hsphsun2.harvard.edu
Subject   st: question about SE when running _metan_ w/ random effects
Date   Sat, 5 Aug 2006 14:41:55 -0700

Dear Stata users of meta-analytic programs,

I am using Stata, specifically -metan-, to run a random effect meta- analysis on continuous data. I have calculate Hedges' g. I also used the sample sizes (with g) to calculate the SE around each g, which I gather is more for a fixed effect model.

If needed, I can also calculate the SE for the difference between the means (but not individually for each mean).

What I have done so far is to run -metan-, plugging in the values for Hedges' g and SE (from the sample sizes), then ask for random effects.

I used the dialog box approach (the "Effect/SE" button under the "Main" tab), but here's how the command line came out:

metan g se, by(drug) random

Am I doing this correctly? In particular, is it OK to use the SE derived from the sample sizes (and g)? If not, what would you suggest?

Thanks very much.

Erick




*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/




© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index