Using standard error in meta() and meta3()

Posted on Sun, 07/03/2016 - 19:23

jasperd Joined: 06/28/2016

Forums

Hi Mike and others,

I've been running some three-level meta-analyses using meta3() with standard error as input instead of variance. However, the description of meta() and meta3() only mention the use of variance as input. Although I am aware it is easy to convert standard error to variance I was wondering whether it is ok to use standard error with meta() and meta3().

Thanks for the help all.

Best,
Jasper

Replied on Sun, 07/03/2016 - 22:41

Mike Cheung Joined: Oct 08, 2009

Hi Jasper, No. If you use

Hi Jasper,

No. If you use standard errors to replace the sampling variances, the parameter estimates and their standard errors are wrong except the rare case that the sampling variances (and standard errors) are all one.

If your standard errors are stored as mydf$se, you may easily convert them into sampling variances by
mydf$v <- mydf$se^2

Best,
Mike

Log in or register to post comments

Replied on Wed, 07/06/2016 - 21:37

jasperd Joined: Jun 28, 2016

Thanks for the fast reply

Thanks for the fast reply Mike!

I will start using sampling variance, thanks for the explanation. Great package.