Is there a way to create the forestplot in R metafor, which presents only subgroup summaries (no individual studies)? Is there a way to create the forestplot in R metafor forest(), which presents only subgroup summaries (no individual studies)?
Like in meta package option study.results=F for forest() does.
Thank you!
 A: Yes, this is possible. Just draw a forest plot based on the summary estimates. Here is an example:
library(metafor)

### calculate log risk ratios and corresponding sampling variances
dat <- escalc(measure="RR", ai=tpos, bi=tneg, ci=cpos, di=cneg, data=dat.bcg)

### meta-regression model with 'alloc' factor
### remove intercept so each estimate is the estimated average log risk ratio for the three levels
res <- rma(yi, vi, mods = ~ alloc - 1, data=dat)
res

### forest plot of the three estimates based on the model
forest(coef(res), sei=res$se, slab=names(coef(res)), 
       atransf=exp, at=log(c(.125, .25, .50, 1, 2)), digits=c(2,3),
       xlab="Risk Ratio", header=c("Allocation Method"))

If you are doing subgrouping, then just collect the estimates and their standard errors into vectors and pass those to forest(). For example:
allocs <- unique(dat$alloc)
res <- lapply(allocs, function(a) rma(yi, vi, data=dat, subset=alloc==a))
est <- sapply(res, coef)
se  <- sapply(res, function(x) x$se)

forest(est, sei=se, slab=allocs, 
       atransf=exp, at=log(c(.125, .25, .50, 1, 2)), digits=c(2,3),
       xlab="Risk Ratio", header=c("Allocation Method"))

