Skip to main content
Fig. 2 | BMC Medical Research Methodology

Fig. 2

From: Heterogeneity estimation in meta-analysis of standardized mean differences when the distribution of random effects departs from normal: A Monte Carlo simulation study

Fig. 2

Absolute bias of the Bayesian estimators

Note. Absolute bias of the Bayesian estimators as a function of the amount of heterogeneity, the number of primary studies, and the average sample size. The results are presented separately for each condition of the shape of the random-effects distribution. FB (mean) = fully Bayesian estimators based on the posterior mean; FB (median) = fully Bayesian estimators based on the posterior median; FB (mode) = fully Bayesian estimators based on the posterior mode; RB = Rukhin Bayes estimator; RBp = positive Rukhin Bayes estimator; BM = Bayes Modal estimator

Back to article page