Hi Jorge,
you can do this using the arguments rightcols and rightlabs (or leftcols and leftlabs). For example, take the first meta-analysis in the help file of metacont():
data(Fleiss1993cont)
# Meta-analysis with Hedges' g as effect measure
#
m1 <- metacont(n.psyc, mean.psyc, sd.psyc, n.cont, mean.cont, sd.cont,
data = Fleiss1993cont, sm = "SMD")
rob <- LETTERS[1:5] # Only as an example
m1$rob <- rob # rob must be a part of the meta-analysis object
forest(m1, rightcols = c("effect", "ci", "w.random", "rob"),
rightlabs = c("SMD", "95%-CI", "Weight (random)", "Risk of bias"))
Note that the column names "effect", "ci", "w.random" are fixed names, as seen in the help of forest.meta().
Best,
Gerta
UNIVERSIT?TSKLINIKUM FREIBURG
Institute for Medical Biometry and Statistics
Dr. Gerta R?cker
Guest Scientist
Stefan-Meier-Stra?e 26 ? 79104 Freiburg
gerta.ruecker at uniklinik-freiburg.de
https://www.uniklinik-freiburg.de/imbi-en/employees.html?imbiuser=ruecker
-----Urspr?ngliche Nachricht-----
Von: Jorge Teixeira via R-sig-meta-analysis <r-sig-meta-analysis at r-project.org>
Gesendet: Montag, 20. M?rz 2023 18:42
An: R meta <r-sig-meta-analysis at r-project.org>
Cc: Jorge Teixeira <jorgemmtteixeira at gmail.com>
Betreff: [R-meta] Add risk of bias to meta's default forest plot
Hi All. Can anyone tell me how to add risk of bias to a meta.cont default
forest plot, without removing any of the typical information?
I was able to add it, but not without removing some other details, which I
don't want to do.
vo2 <- metacont(en , em, esd, cn, cm, csd, study, method.tau = "REML",
prediction = TRUE, comb.random = TRUE, data = dat_vo2, sm = "MD")
vo2
forest.meta(vo2,
sortvar = study)
In this case, I have that information in variable "rob".
Thank you.
_______________________________________________
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