Skip to content

[R-meta] meta-analysis of other values than effect size

3 messages · Gladys Barragan-Jason, Dr. Gerta Rücker, James Pustejovsky

Original
Gladys Barragan-Jason
# 
Dear all,

I would like to know whether it is possible to conduct a meta-analysis on
the mean values of a variable (for which I have sample size, standard
deviation, mean age, gender distribution, country etc.). Can such an
analysis be performed in a way similar to a meta-analysis of effect sizes
where several samples came from the same study and which take the number of
participants etc... into account?

Best wishes,

Gladys
Dr. Gerta Rücker
# 
Hi Gladys,
Of course this is possible, for example using function metamean() from R package meta. The main arguments are n, mean, sd, studlab, where sd is the standard deviation (not to be confused with the standard error), and studlab is a study label. See help(metamean). You can then also perform subgroup analyses or metaregression.

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

Von: Gladys Barragan-Jason via R-sig-meta-analysis <r-sig-meta-analysis at r-project.org>
Gesendet: Montag, 17. November 2025 16:00
An: R meta <r-sig-meta-analysis at r-project.org>
Cc: Gladys Barragan-Jason <gladou86 at gmail.com>
Betreff: [R-meta] meta-analysis of other values than effect size

Dear all,

I would like to know whether it is possible to conduct a meta-analysis on the mean values of a variable (for which I have sample size, standard deviation, mean age, gender distribution, country etc.). Can such an analysis be performed in a way similar to a meta-analysis of effect sizes where several samples came from the same study and which take the number of participants etc... into account?

Best wishes,

Gladys
--
------------------------------------------
Gladys Barragan-Jason, PhD.  Website<https://sites.google.com/view/gladysbarraganjason/home> / Site web<https://sites.google.com/view/frgladysbarragan-jason/accueil>
Charg?e de recherche, CRCN
Station d'Ecologie Th?orique et Exp?rimentale (SETE)
Centre National de la Recherche Scientifique (CNRS)
2 route du CNRS, 09200 Moulis
Equipe LINKING
Groupe de recherche RISE (Recherche Interdisciplinaire pour la Soutenabilit? Environnementale)
Coordinatrice du r?seau ETHNOECO
07 72 07 93 31
[cid:image001.png at 01DC57DC.DBD5B630][cid:image002.png at 01DC57DC.DBD5B630]



-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://stat.ethz.ch/pipermail/r-sig-meta-analysis/attachments/20251117/0bd1523f/attachment-0001.html>

-------------- next part --------------
A non-text attachment was scrubbed...
Name: image001.png
Type: image/png
Size: 7519 bytes
Desc: image001.png
URL: <https://stat.ethz.ch/pipermail/r-sig-meta-analysis/attachments/20251117/0bd1523f/attachment-0002.png>

-------------- next part --------------
A non-text attachment was scrubbed...
Name: image002.png
Type: image/png
Size: 7125 bytes
Desc: image002.png
URL: <https://stat.ethz.ch/pipermail/r-sig-meta-analysis/attachments/20251117/0bd1523f/attachment-0003.png>
James Pustejovsky
# 
Hi Gladys,

In short, yes. It's entirely possible and conventional to use group means
(or raw percentages, or group-specific SDs) as the effect size in a
meta-analysis. The metafor package's escalc() function provides options for
calculating the standard errors of such effect sizes; see details here:
https://wviechtb.github.io/metafor/reference/escalc.html#-outcome-measures-for-individual-groups
Here is an example of a synthesis that uses percentage as the effect size
metric:
https://srcd.onlinelibrary.wiley.com/doi/full/10.1111/cdev.13039

Kind Regards,
James

On Mon, Nov 17, 2025 at 9:02?AM Gladys Barragan-Jason via
R-sig-meta-analysis <r-sig-meta-analysis at r-project.org> wrote:

            

      
      
      
    

        

      
      
    

        
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://stat.ethz.ch/pipermail/r-sig-meta-analysis/attachments/20251117/8d211630/attachment-0001.html>

-------------- next part --------------
A non-text attachment was scrubbed...
Name: image004.png
Type: image/png
Size: 7125 bytes
Desc: not available
URL: <https://stat.ethz.ch/pipermail/r-sig-meta-analysis/attachments/20251117/8d211630/attachment-0002.png>

-------------- next part --------------
A non-text attachment was scrubbed...
Name: image003.png
Type: image/png
Size: 7519 bytes
Desc: not available
URL: <https://stat.ethz.ch/pipermail/r-sig-meta-analysis/attachments/20251117/8d211630/attachment-0003.png>