Figure 4
From: Subgroup effects despite homogeneous heterogeneity test results
Modified forest plot of a meta-analysis on five studies on the effects of amoxicillin in children with acute otitis media, ordered by the proportion of bilateral otitis in each study. The treatment effects and corresponding 95% confidence intervals of five out of six randomized trials included in an IPD meta-analysis on the effects of amoxicillin in children with acute otitis media are shown [13]. The dashed line (- - - -) indicates no treatment effect. The studies are ordered by the proportion of children with bilateral otitis. In the excluded study, bilaterality was not registered.