Absolute relative bias of Fed-GLMM and meta-analysis estimates relative to gold-standard pooled analysis across simulation replicates.

We compared the accuracy of Fed-GLMM with the standard meta-analysis by calculating the absolute relative difference from the gold-standard pooled analysis for estimating the coefficient of a binary exposure variable. The underlying model has a binary outcome, a binary exposure, three more covariates with 8 site-specific fixed effect coefficients for the normally distributed covariate and a patient-level random intercept. The model also includes 8 site-specific parameters for variance components. We considered 25 combinations of outcome and exposure prevalence each with 100 simulation replicates to assess the model accuracy. Fed-GLMM achieved almost identical results as the pooled analysis for all simulation replicates after 1–2 iterations, while the meta-analysis demonstrated greater bias and variance relative to the pooled analysis across all simulation replicates and prevalence settings. Abbreviations: EY—Prevalence of Outcome; EX—Prevalence of Exposure. (JPG)