[R-meta] : Metafor package, Omnibus test

[Viechtbauer, Wolfgang (SP)]

Dear Annika,

It is indeed a Wald-type test. See also:

http://www.metafor-project.org/doku.php/tips:testing_factors_lincoms

Best,
Wolfgang

-----Original Message-----
From: R-sig-meta-analysis [mailto:r-sig-meta-analysis-bounces using r-project.org] On Behalf Of Michael Dewey
Sent: Monday, 23 July, 2018 16:46
To: Annika Vater; r-sig-meta-analysis using r-project.org
Subject: Re: [R-meta] : Metafor package, Omnibus test

Annika Vater <annika.vater using googlemail.com> wrote :

Dear Annika

You could always experiment with anova.rma() which specifies what sort of test it is doing. Given the documentation for anova.rma I suspect the answer to your question is Wald-type but you can reassure yourself with an experiment.

Michael

> Dear all,
> 
> I have a question regarding the metafor package.
> For the Test of Moderators there is reported a value for QM and a p-value.
> In the Documentation it's written that the test used is an Omnibus Test of
> Parameters - but it's not clear if it's a Wald-Test or a
> Likelihood-Ratio-Test.
> Could you tell me which test is used?
> I assume it's a Wald-Test, but am not sure at all.
> 
> Thank you for supporting in advance!
> All the best,
> Annika