[R-meta] correct tau interpretation three-level meta-analysis

[Viechtbauer, Wolfgang (SP)]

Dear Filippo,

The variance component corresponding to 'study' is the amount of heterogeneity in the average true effects of the various studies (i.e., studies with multiple outcomes have an average true effect). The variance component corresponding 'outcome' is the amount of heterogeneity in the true effects around those average true effects of the studies.

So, I would say that neither is really the standard heterogeneity, but that also depends on what exactly you mean by that.

Best,
Wolfgang

>-----Original Message-----
>From: R-sig-meta-analysis [mailto:r-sig-meta-analysis-bounces using r-project.org] On
>Behalf Of Filippo Gambarota
>Sent: Sunday, 04 July, 2021 12:36
>To: r-sig-meta-analysis using r-project.org
>Subject: [R-meta] correct tau interpretation three-level meta-analysis
>
>Hi,
>I'm conducting a meta-analysis using a three-level model because I
>have multiple effects within the same study. My model is something
>like this:
>
>```
>rma.mv(yi, vi, random = ~1|study/outcome)
>```
>My question is simply how to correctly interpret tau at the outcome
>level. The tau at the study level is basically the standard
>heterogeneity. The tau at the outcome level is the average variability
>within a cluster (study)?
>Thanks
>
>--
>Filippo Gambarota
>PhD Student - University of Padova
>Department of Developmental and Social Psychology
>Website: filippogambarota.netlify.app
>Research Group: Colab   Psicostat