Optimal trial design selection: a comparative analysis between two-arm and three-arm trials incorporating network meta-analysis for evaluating a new treatment

Table 2 Power difference and sample size allocation among three trial settings in Simulation Study II: Treatment A is TULA, Treatment B is TRIM. The estimated risk of A and B are 0.166 and 0.553 from the existing network meta-analysis

		Sample size allocation in different trial setting							Simulation
		(1)		(2)			(3)		Power (%)			Power Difference (%)
Risk of Z	N	Z	A	Z	A	B	Z	B	(1)	(2)	(3)	(2) - (1)	(2) - (3)
0.35	100	44	56	46	38	16	51	49	52.2	54.3	50.5	2.0	3.7
0.36	100	44	56	46	38	16	51	49	56.5	58.4	54.8	2.0	3.7
0.37	100	44	56	46	38	16	51	49	60.4	62.6	59.2	2.2	3.4
0.38	100	43	57	46	38	16	51	49	63.9	66.5	63.2	2.6	3.2
0.39	100	43	57	46	38	16	50	50	67.7	70.3	67.5	2.6	2.8
0.40	100	43	57	46	38	16	50	50	71.2	74.0	71.3	2.9	2.8
0.41	100	43	57	45	39	16	50	50	74.5	77.6	74.8	3.1	2.9
0.42	100	43	57	45	39	16	50	50	77.6	80.7	78.0	3.1	2.7
0.43	100	43	57	45	39	16	50	50	80.5	83.5	80.9	3.0	2.6

ISSN: 1471-2288