standardizing meta-analysis values for forest plot using meta package

[May Blake]

Hello, I have a mixture of mean (se) and R/R2 values to be used for a meta-analysis. I am using STATA meta package to conduct my analysis for the pooled estimates. Below is a sample of my data. I am not sure how to convert the R/R2 values so that they are in the same standard format with the mean (se). Any help will be greatly appreciated. I could conduct the analysis using groupings but then my pooled estimates would be wrong since they will be based on two separate measurements.

----------------------- copy starting from the next line -----------------------

meta set mean se, random
meta summarize
meta forestplot
end

------------------ copy up to and including the previous line ------------------



----------------------- copy starting from the next line -----------------------

* Example generated by -dataex-. For more info, type help dataex
clear
input byte StudyID int(Year Samplesizeincluded) double(mean se R R2 OR) str7 P float group
10 2020 20    .   .  .01 . . ""      2
 2 2015 88    .   .  .19 . . "0.01"  2
 8 2019 64    .   .  .18 . . "0.05"  2
 5 2017 20    .   . -.23 . . ".031"  2
 2 2015 38    .   .  .33 . . "0.01"  2
12 2021 53 18.4   5  .03 . . "0.001" 1
14 2021 66 2.04 .49  .12 . . "0.05"  1
 7 2018 63 2.44 .49  .35 . . "0.01"  1
end

------------------ copy up to and including the previous line ------------------

Listed 8 out of 8 observations

[Tiago Pereira]

What does R and R2 mean? If they mean correlation coefficient (Pearson) and coefficient of determination, you need to perform a meta-analysis of correlation coefficients.