Skip to main content
Fig. 4 | BMC Medicine

Fig. 4

From: How robust are findings of pairwise and network meta-analysis in the presence of missing participant outcome data?

Fig. 4

A panel of probability density plots of the summary standardised mean difference (SMD) of supplementary feeding versus the control intervention from Sguassero et al. [36]. The red line indicates the posterior distribution of the SMD under the primary analysis. The black lines indicate the posterior distribution of the SMD under the alternative re-analyses. The alternative re-analyses refer to 24 different assumptions about the informative missingness difference of means parameter in the supplementary feeding (facets at the top of the panel) and the control intervention (facets at the left of the panel). The blue area corresponds to the Kullback-Leibler divergence (KLD) measure. The vertical dotted line refers to SMD equal to zero (no difference). The grey rectangular indicates the 95% credible interval of SMD under the corresponding re-analysis

Back to article page