Figure 3 of Agarwal, Mol Vis 2015; 21:612-620.

Figure 3. Begg’s funnel plot with the Egger’s test for publication bias for association of TGF-β levels in aqueous humor with risks of OAG. The vertical line in the funnel plot indicates the fixed-effects summary estimate, whereas the diagonal lines represent the pseudo-95% confidence interval (CI) limits concerning the effect estimate. In the absence of publication bias, studies are distributed symmetrically to the right and left of the vertical line. The blue symbols refer to the observed studies, while the red is the imputed studies, that is, expected if larger numbers of studies with negative results have been included in the analysis. A: Total transforming growth factor (TGF)-β2 levels in open-angle glaucoma (OAG), PEgger’s test=0.02 B: Active TGF-β levels in OAG, PEgger’s test=0.82.