Table 5: N = 120. Designs for testing H0:p p0 vs. H1:p > p0 with = 0:05 and power at least 80% at p1 = p0 + 0:2. For each setting the Rows 1-3 contain the Types 1-3 two-stage designs. The left and rights parts are for the first type and second type of optimal designs.

p0

(1-stage)

 2-stage minimizing EN0 2-stage minimizing n2
Design EN0 n2 P
ET0		 Design EN0 n2 P
ET0
0.1
(21; 4) 		(14, 3; 20,4)
(12, 2; 21,4)
(12, 2, 3; 21, 4 		19.8
15.1
14.9 		20
21
21 		0.03
0.66
0.68 		(13, 3; 20, 4)
(12, 2; 21,4)
(13, 1, 3; 21, 4) 		19.8
15.1
18.2 		20
21
20 		0.03
0.66
0.26
0.2
(26; 8) 		(16, 6; 26,8)
(17, 4; 26,8)
(13, 3, 5; 26, 8) 		25.8
21.1
19.3 		26
26
26 		0.02
0.54
0.52 		(16, 6; 26,8)
(17, 4; 26,8)
(13, 3, 5; 26, 8) 		25.8
21.1
19.3 		26
26
26 		0.02
0.54
0.52
0.3
(29; 12) 		(16, 8; 29, 12)
(22, 8; 29, 12)
(19, 7, 9; 29, 12) 		28.8
24.2
22 		29
29
29 		0.02
0.68
0.7 		(16, 8; 29, 12)
(22, 8; 29, 12)
(19, 7, 9; 29, 12) 		28.8
24.2
22 		29
29
29 		0.02
0.68
0.7
0.4
(31; 16) 		(20, 12; 29,15)
(16, 7; 31, 16)
(19, 9, 12; 31, 16) 		28.9
23.1
22.8 		29
31
31 		0.01
0.53
0.69 		(20, 12; 29, 15)
(16, 7; 31, 16)
(20, 1, 12; 29, 15) 		28.9
23.1
28.9 		29
31
29 		0.01
0.53
0.01
0.5
(29; 18) 		(15, 11; 29,18)
(22, 12; 29,18)
(20, 11, 14; 29, 18) 		28.8
24.8
23.5 		29
29
29 		0.01
0.59
0.61 		(15, 11; 29,18)
(22, 12; 29, 18)
(20, 11, 14; 29, 18) 		28.8
24.8
23.5 		29
29
29 		0.01
0.59
0.61
0.6
(28; 20) 		(24, 19; 28,20)
(17, 12; 28,20)
(17, 12, 14; 28, 20) 		28
19.7
19.6 		28
28
28 		0.01
0.75
0.76 		(24, 19; 28,20)
(17, 12; 28,20)
(17, 12, 14; 28, 20) 		28
19.7
19.6 		28
28
28 		0.01
0.75
0.76
0.7
(23; 19) 		(19, 16; 23,19)
(11, 9; 22, 18)
(12, 10, 11; 22, 18) 		22.9
14.3
14.3 		23
22
22 		0.03
0.7
0.77 		(19, 16; 23,19)
(11, 9; 22, 18)
(12, 10, 11; 22, 18) 		22.9
14.3
14.3 		23
22
22 		0.03
0.7
0.77