[R-meta] Forest plot for multi-level meta-analysis

Yogev Kivity yogev_k @ending from y@hoo@com
Fri May 11 21:38:50 CEST 2018


Hi all,
I am conducting a multi-level meta-analysis in metafor. In total, I am including 803 effect sizes, clustered in 91 groups of participants, which in turn are clustered in 69 studies.
I would like to graphically present the effect sizes in a forest plot. However, given the number of effect sizes and given that I will be presenting the plot at a talk, I am concerned that plotting all of the individual effect sizes will not be very informative but rather confusing to the audience (even if I used a caterpillar plot).
I was wondering whether it makes sense to present the effect sizes at the study level (i.e., the aggregated effect size across groups and individual effect size, thus resulting in 69 effect sizes to plot), and if so - whether there is an easy way to do in R.
I would appreciate any thoughts and advice on this issue.
Thanks,Yogev
--

Yogev Kivity, Ph.D.
Postdoctoral Fellow
Department of Psychology
The Pennsylvania State University
Bruce V. Moore Building
University Park, PA 16802
Office Phone: (814) 867-2330


	[[alternative HTML version deleted]]



More information about the R-sig-meta-analysis mailing list