Table 1.

Example of treatment hierarchies from different ranking metrics for a network of nine antihypertensive treatment for primary prevention of cardiovascular disease

Treatment	Original data			Fictional data with increased precision for conventional treatment versus ARB
	${\mathit{p}}_{\mathit{B}\mathit{V}}$Ranks	${\mathit{S}\mathit{U}\mathit{C}\mathit{R}\mathit{A}}_{\mathit{F}}$Ranks	Relative treatment effect ranks	${\mathit{p}}_{\mathit{B}\mathit{V}}$Ranks	${\mathit{S}\mathit{U}\mathit{C}\mathit{R}\mathit{A}}_{\mathit{F}}$Ranks	Relative treatment effect ranks
Conventional	1	6	3.5	3	4	3.5
Diuretic/beta-blocker	2	1	1	1	1	1
ARB	3	3	3.5	4.5	3	3.5
CCB	4	2	2	2	2	2
Alpha-blocker	5	7	7	4.5	7	7
ACE-inhibitor	6	4	5	6.5	5	5
Diuretic	7	5	6	6.5	6	6
Placebo	8.5	9	9	8.5	9	9
Beta-blocker	8.5	8	8	8.5	8	8

Relative treatment effect stands for the relative treatment effect against fictional treatment of average performance. The first three rankings from the left-hand side are obtained using the original data; the equivalent three rankings on the right-hand side are produced by reducing the standard error of the conventional versus ARB treatment effect from 0.7 to a fictional value of 0.01.

ACE, angiotensin converting enzyme; ARB, angiotensin receptor blockers; CCB, calcium channel blockers; pBV, probability of producing the best value; SUCRA_F, surface under the cumulative ranking curve (calculated in frequentist setting).