Effect Size Calculation with metafor (using "SMD"): insert standard deviation of difference of groups rather than group-specific SDs?

Question

I am currently trying to calculate effect sizes for a meta-analysis that I am conducting. I am interested in calculating a standardized mean difference for paired data. I am using the escalc function ("SMD") of the package metafor to do this.

I have realized why extracting data that some papers only report the standard deviation of the difference scores rather than the SDs of the two groups specifically. When this is the case, how can I implement them into the escalc function, as "SMD" always seems to require the groups' SDs.

Thanks a lot!

score 1 · Answer 1 · answered Sep 27 '21 at 17:32

Measure SMD is not for paired data. See help(escalc) or go to https://wviechtb.github.io/metafor/reference/escalc.html and search for measures SMCC and SMCR. The section that starts with "A few notes about the change score measures." is particularly relevant.

Effect Size Calculation with metafor (using "SMD"): insert standard deviation of difference of groups rather than group-specific SDs?

1 Answers1