Take the 2-minute tour ×
Cross Validated is a question and answer site for people interested in statistics, machine learning, data analysis, data mining, and data visualization. It's 100% free, no registration required.

I am conducting a meta-analysis and am trying to produce a forest plot displaying the mean weighted effect size with and without the outliers. I looked on so many websites and tried a lot of syntaxes, however, didn't really find anything about what I am looking for.

Assume there are 10 studies in the meta-analysis. Outlier analyses showed that Study 3 is an outlier leading to an overestimation of the mean weighted ES. Accordingly, I calculate a mean ES with (k = 10) and without the outlier (k = 9). I would like to display the studies sorted according to their ES and report both Mean ESs in the forest plot. I would appreciate any help and/or advice.

Study3 Study9 Study5 ... Study7

Mean ES (k = 10) Mean ES (k = 9)

share|improve this question
    
I also tried to produce a graphs as the link below metafor-project.org/doku.php/plots:forest_plot_with_subgroups however, suddenly, the program didn't show the graphs in the output anymore after I used the command dev.off(). The graphs was saved on my computer, but I would prefer to see the graph in the output (I use R Studio) before I save it. How can I change it back? –  Natalie Jul 11 at 5:27
add comment

1 Answer 1

You missed metafor's function addpoly(). Here is a fully reproducible example:

library(metafor)

data(dat.bcg)

## REM (k = 13)
res <- rma(ai=tpos, bi=tneg, ci=cpos, di=cneg, data=dat.bcg, measure="RR",
           slab=paste(author, year, sep=", "), method="REML")

## REM (k = 11; 'outliers' removed)
res2 <- rma(ai=tpos, bi=tneg, ci=cpos, di=cneg, data=subset(dat.bcg, trial < 12),
            measure="RR", slab=paste(author, year, sep=", "), method="REML")

## Forest plot
forest(res, xlim=c(-16, 6), at=log(c(.05, .25, 1, 4)), atransf=exp,
       ilab=cbind(dat.bcg$tpos, dat.bcg$tneg, dat.bcg$cpos, dat.bcg$cneg),
       ilab.xpos=c(-9.5,-8,-6,-4.5), cex=.75, ylim=c(-3, 16),
       order="obs", xlab="Relative Risk", mlab="RE Model for All Studies (k = 13)")

## Add second summary effect size
addpoly(res2, atransf=exp, mlab="RE Model without 'outliers' (k = 11)", cex=.75)

Here is the result:

enter image description here

share|improve this answer
    
Thank you very much. I reproduced the graph above, and was also able to do it with my results. So happy, it finally worked. –  Natalie Jul 12 at 5:18
    
@Natalie Glad that I could help! Please consider to accept my answer if it was helpful. –  Bernd Weiss Jul 12 at 7:05
add comment

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.