[R-meta] How to examine the moderating effect of sex in a meta-analysis of group differences?

[Will Hopkins]

I devised a cool solution to this problem some years ago. I include a modifying covariate called Maleness, with values ranging from 0 to 1, depending on the proportion of males. (You could, of course, make it Femaleness, but the values of 0 and 1 would have the wrong phallic significance.) This approach extends to other binary subject characteristics, such as sedentary vs active. 

It sounds like you are including effects in control and intervention groups as repeated measurements in your meta-analysis, so interact Maleness with Treatment, and make sure you include appropriate additional random effects to account for the repeated measurement. I don't know how it works in metafor, but in SAS it's:
random StudyID;
random EstimateID/Group=Treatment;

Will

-----Original Message-----
From: R-sig-meta-analysis <r-sig-meta-analysis-bounces using r-project.org> On Behalf Of Catia Oliveira via R-sig-meta-analysis
Sent: Thursday, October 12, 2023 4:37 AM
To: R meta <r-sig-meta-analysis using r-project.org>
Cc: Catia Oliveira <catia.oliveira using york.ac.uk>
Subject: [R-meta] How to examine the moderating effect of sex in a meta-analysis of group differences?

Dear all,

What is the best way of examining the moderating effect of sex when looking at group differences in variable X? I considered using the ratio between males/females, but this ratio often differs between groups, where the control group has more females and the intervention group has more males for example. Are there any clever solutions to this problem?

Best wishes,

Catia

--
Cátia Margarida Ferreira de Oliveira
Research Associate
Department of Psychology, Room C222
University of York, YO10 5DD
Twitter: @CatiaMOliveira
pronouns: she, her

	[[alternative HTML version deleted]]

_______________________________________________
R-sig-meta-analysis mailing list @ R-sig-meta-analysis using r-project.org To manage your subscription to this mailing list, go to:
https://stat.ethz.ch/mailman/listinfo/r-sig-meta-analysis