[R-meta] How could I conduct meta-analysis with single group percentage outcomes?
When I commented on your post on CrossValidated I suggested two packages which you could investigate. Which of them did you decide on and where have you got stuck? Michael
On 21/03/2022 15:57, Yue Yin wrote:
Hi, all, I want to conduct a meta-analysis using R on a bunch of articles. The outcomes are in percentage format and it is single group. I am wondering how could I use R to do this kind of meta-analysis? In the beginning, I thought that I could use metaprop, but after I checked the example, I think I can only use metaprop when I want to compute the proportion. For example, we have several events out of the total sample size for each article, and we can use metaprop to compute it. And because each individual has percentage, I can't back convert the percentage to the number of event. In my example, which R statement or argument should I use to deal with single group percentage data? I hope I could get the following forest plot with the percentage, standard error and sample size on the left column (I found this example in an article, and they also have one group percentage data, but I can't find which R statement or argument I can use): [image: Example forest plot with single group percentage outcome] Could anyone help me with it? Thank you! [[alternative HTML version deleted]]
_______________________________________________ R-sig-meta-analysis mailing list @ R-sig-meta-analysis at r-project.org To manage your subscription to this mailing list, go to: https://stat.ethz.ch/mailman/listinfo/r-sig-meta-analysis