I am following the following book: https://bookdown.org/MathiasHarrer/Doing_Meta_Analysis_in_R/multilevel-ma.html
I can’t choose which estimator to choose: REML or CR2 with Wild Bootstrap.
Or maybe run them both and present as a sensitivity analysis, although I can’t see any other meta-analyses which did so, so maybe it will further confuse the readership of the article.
Some details:
I have a small sample size (both can help with it)
and dependent effect-sizes (CR2 is the best for it)
and my outcome is a continuous variable (REML seems to be better suited for that)
Could you kindly advice what you did if you had a similar question? Thanks!