[R-meta] Quick question about multiple independent samples within one study

[Guido Schwarzer]

Dear Anna-Lena,

I would suggest that you have a look at Rücker et al. (2017) as well as 
sections 16.5.4 and 16.5.5 of the Cochrane Handbook 
(https://handbook-5-1.cochrane.org/).

These papers deal with multiple treatment groups, however, the same 
arguments apply if you have different age groups etc. within a study.

In summary, it is fine to include multiple independent groups from a 
study under a fixed effect model. However, you should combine the groups 
within a study under the random effects model.

Best wishes, Guido

Reference:
Rücker G, Cates CJ, Schwarzer G. Methods for including information from 
multi-arm trials in pairwise meta-analysis. Res Synth Methods. 
2017;8(4):392–403.