[R-meta] Gender meta-analysis

[Viechtbauer, Wolfgang (SP)]

Hi Julie,

If you want to include multiple estimates that are obtained from the same sample repeatedly over time, then one needs to account for the dependency in the sampling errors of the estimates over time and for the dependency in the underlying true outcomes. Models of this type have been described in:

Trikalinos, T. A., & Olkin, I. (2012). Meta-analysis of effect sizes reported at multiple time points: A multivariate approach. Clinical Trials, 9, 610-620.

Ishak, K. J., Platt, R. W., Joseph, L., Hanley, J. A., & Caro, J. J. (2007). Meta-analysis of longitudinal studies. Clinical Trials, 4, 525-539.

Musekiwa, A., Manda, S. O., Mwambi, H. G., & Chen, D. G. (2016). Meta-analysis of effect sizes reported at multiple time points using general linear mixed model. PLOS ONE, 11(10), e0164898.

Implementations of these methods can be found under:

help(dat.fine1993)
help(dat.ishak2007)

Construction of the var-cov matrix of the sampling errors can be difficult. As an alternative, one could use cluster-robust inference methods.

Best,
Wolfgang

-----Original Message-----
From: R-sig-meta-analysis [mailto:r-sig-meta-analysis-bounces using r-project.org] On Behalf Of Julie Webbs
Sent: Tuesday, 18 December, 2018 18:33
To: r-sig-meta-analysis using r-project.org
Subject: [R-meta] Gender meta-analysis

I have the data for 10 years according to gender and performance. If  I
assume female as a group and males as another group , will it be possible
to run a meta-analysis using 10 years, assuming each year as a study?
Questions for measuring performance are different, but samples more or less
the same with different people.

Thank you for your advice.