Figure 1.

Graphical depiction of consistency, loop inconsistency and design inconsistency. (a) consistency: there is no conflict among the three sources of evidence from pairwise trials (on A vs B, A vs C and B vs C); (b) loop inconsistency: evidence on the direct comparison of A vs C (dashed line) conflicts with evidence drawn via the indirect comparison involving A vs B and B vs C (solid lines). (c) loop inconsistency: alternative scenario, indistinguishable from (b) without additional evidence; (d) consistency: three-arm trials, in which consistency is inevitable; (e) design inconsistency: evidence from the three-arm trial(s) is inconsistent with that from the two-arm trials; (f) design inconsistency and loop inconsistency: pairwise trials display loop inconsistency, whereas the three-arm trial conflicts with at least one pairwise trial, reflecting design inconsistency; and (g) design inconsistency without loop inconsistency: evidence from the three-arm trial(s) is inconsistent with that from the two-arm trials, which are themselves consistent