NMA Inconsistency

Detect inconsistency between direct and indirect evidence in network meta-analysis. Performs node-splitting (Dias et al. 2010) on every comparison with a closed loop, and a global design-by-treatment test (Higgins et al. 2012).

Input

Contrasts — A, B, effect, SE Multiple rows per comparison allowed.

Node-split per comparison

Comparison	Direct	Indirect	Difference	z	p

Design-by-treatment (global)

Net-split forest

Reading the plot: direct and indirect whiskers should overlap for a consistent network. Non-overlapping whiskers with |z| > 1.96 indicate a specific loop with inconsistency. The global design-by-treatment test is the omnibus check.

Node-splitting: Dias S et al. Stat Med 2010;29:932-944. Design-by-treatment inconsistency model: Higgins JPT, Jackson D, Barrett JK et al. Res Synth Methods 2012;3:98-110. Caveat: this tool uses fixed-effect weights (no shared τ²) for both consistency and inconsistency models. For heterogeneous networks the Q-statistics are inflated and the LR test is anti-conservative; cross-check with R netmeta::decomp.design. Recommended k≥5 per design.