Fig 1.
Boxplots of the estimated mean differences in 10,000 simulated meta-analyses.
The true between-study standard deviation τ increased from 0 (panels a and b) to 1 (panel c). The number of studies in each meta-analysis N increased from 5 (panel a) to 50 (panels b and c). The true mean difference Δ (horizontal dotted line) was 0.
Fig 2.
Boxplots of the estimated standardized mean differences in 10,000 simulated meta-analyses.
For each sample size range on the horizontal axis, the left gray box was obtained using Cohen’s d, and the right black box was obtained using Hedges’ g. The true between-study standard deviation τ increased from 0 (upper and middle panels) to 0.5 (lower panels). The number of studies in each meta-analysis N increased from 5 (upper panels) to 50 (middle and lower panels). The true standardized mean difference θ (horizontal dotted line) increased from 0 (left panels) to 1 (right panels).
Fig 3.
Boxplots of the estimated log odds ratios in 10,000 simulated meta-analyses.
The true between-study standard deviation τ increased from 0 (upper and middle panels) to 0.5 (lower panels). The number of studies in each meta-analysis N increased from 5 (upper panels) to 50 (middle and lower panels). The true log odds ratio θ (horizontal dotted line) increased from 0 (left panels) to 1.5 (right panels).
Fig 4.
Boxplots of the estimated log risk ratios in 10,000 simulated meta-analyses.
The true between-study standard deviation τ was 0 (i.e., the simulated studies were homogeneous). The number of studies in each meta-analysis N increased from 5 (upper panels) to 50 (lower panels). The true log risk ratio θ (horizontal dotted line) increased from 0 (left panels) to 0.3 (right panels).
Fig 5.
Boxplots of the estimated risk differences in 10,000 simulated meta-analyses.
The true between-study standard deviation τ was 0 (i.e., the simulated studies were homogeneous). The number of studies in each meta-analysis N increased from 5 (upper panels) to 50 (lower panels). The true risk difference θ (horizontal dotted line) increased from 0 (left panels) to 0.2 (right panels).
Table 1.
Bias of the estimated overall effect size in the simulation studies.
Table 2.
Coverage probability (in percentage, %) of the estimated overall effect size’s 95% confidence interval in the simulation studies.