Table 3.

Hypothetical Example 1. Conjunctive probability at each analysis and conjunctive power when the BH procedure is used.

Correlation	Boundary function combination	Stopping probability (%) at each analysis (month)			Conjunctive power (%)
		36 (l =1)	48 (l =2)	60 (l =3)
0.3	(a) OBF-OBF	1.31	36.23	40.16	77.71
	(b) OBF-POC	3.88	36.00	36.56	76.43
	(c) POC-OBF	7.14	39.98	24.09	71.20
	(d) POC-POC	21.35	27.79	21.02	70.17
0.5	(a) OBF-OBF	1.37	36.41	39.95	77.73
	(b) OBF-POC	3.96	36.13	36.40	76.48
	(c) POC-OBF	7.32	40.00	23.92	71.24
	(d) POC-POC	21.59	27.74	20.91	70.24
0.8	(a) OBF-OBF	1.58	36.94	39.31	77.83
	(b) OBF-POC	4.20	36.53	35.94	76.67
	(c) POC-OBF	7.90	40.06	23.40	71.36
	(d) POC-POC	22.35	27.56	20.55	70.46

The accrual duration is τ_A =36 months and follow-up duration is common for MACE and CVD-or-HHF, ${\tau }_{f_1}={\tau }_{f_2}={\tau }_f=24$ months. The HR is ψ₁ =0.85 for MACE and ψ₂ =0.80 for CVD-or-HHF. The proportion of survivors after the follow-up duration is common for MACE and CVD-or HHF $S_1^{(1)}(60)=S_2^{(1)}(60)=85\text{\%}$. Three analyses at 36, 48 and 60 months are planned for MACE and CVD-or HHF. The correlation is assumed to be ρ =0.3, 0.5 and 0.8. The conjunctive probability at each analysis and conjunctive power are calculated under a sample size of 14,466 with $S_1^{(1)}(60)=85\text{\%}$, which provides at least 80% power to detect 15% reduction in the HR for MACE at the 1.25% significance level by a one-sided logrank test in the fixed-sample design.