= Solution
A <network meta-analysis> can offer three distinct benefits, assuming a connected treatment network and credible <transitivity in network meta-analysis>.
* \b[Comparisons without a direct trial.] A path through common comparators permits an <indirect treatment comparison> of treatments that have never been randomized against one another.
* \b[Greater precision.] Combining consistent direct and indirect evidence can reduce the <variance> of a treatment-effect estimate and make more complete use of the trials than separate pairwise <meta-analyses>.
* \b[Coherent decisions across many treatments.] A joint <statistical model> estimates all relative effects on one scale, allowing treatment rankings and their uncertainty to inform a choice among several options rather than presenting disconnected pairs.
These are potential benefits, not guarantees: heterogeneous <effect modifiers>, inconsistent evidence, disconnected networks or imprecise rankings can defeat them.
Back to article page
