model measure MAJOR

[davidealbertoni]

Hello! I’m using the MAJOR module in Jamovi to run a meta-analysis based on correlation coefficients.

I’d like to ask: what is the actual difference between selecting “raw correlation coefficient” and “Fisher’s r-to-z transformation coefficient” in the "model option" --> "model measure" section? Does this choice only affect how the results are displayed in the output, or does it also change how the meta-analysis is conducted?

In other words, if I select “raw correlation coefficient”, is the meta-analysis still performed on Fisher’s z-transformed values internally and then back-transformed for reporting?

Thanks a lot in advance!

Davide

[yurismol]

I think this question is for the creator of the metafor package (Wolfgang Viechtbauer), not the MAJOR module, which only translates parameters.
The documentation describes the comparative use of the parameters "COR" for the raw correlation coefficient, "UCOR" for the raw correlation coefficient corrected for its slight negative bias (based on
equation 2.3 in Olkin & Pratt, 1958), "ZCOR" for Fisher’s r-to-z transformed correlation coefficient (Fisher, 1921).
https://www.metafor-project.org/doku.php/metafor
https://cran.r-project.org/web/packages ... etafor.pdf