Table 5.
Comparison of different two-arm trial designs of size T = 148. Fa: Fisher's adjusted test; α: type-I error; 1 − β: power; p*: expected proportion of patients in the trial assigned to the best treatment; ENS: expected number of patient successes; UB: upper bound
| Crit. value |
H0 : p0 = p1 = 0.3 |
H1 : p0 = 0.3, p1 = 0.5 |
|||||
|---|---|---|---|---|---|---|---|
| α | p* (s.e.) | ENS (s.e.) | 1− β | p* (s.e.) | ENS (s.e.) | ||
| FR | 1.645 | 0.052 | 0.500 (0.04) | 44.34 (5.62) | 0.809 | 0.501 (0.04) | 59.17 (6.03) |
| TS | 1.645 | 0.066 | 0.499 (0.10) | 44.39 (5.58) | 0.795 | 0.685 (0.09) | 64.85 (6.62) |
| UCB | 1.645 | 0.062 | 0.499 (0.10) | 44.30 (5.60) | 0.799 | 0.721 (0.07) | 66.03 (6.54) |
| RBI | 1.645 | 0.067 | 0.502 (0.14) | 44.40 (5.57) | 0.763 | 0.737 (0.07) | 66.43 (6.54) |
| RGI | 1.645 | 0.063 | 0.500 (0.11) | 44.40 (5.61) | 0.785 | 0.705 (0.07) | 65.46 (6.40) |
| CB | Fa | 0.046 | 0.528 (0.44) | 44.34 (5.55) | 0.228 | 0.782 (0.35) | 67.75 (12.0) |
| WI | Fa | 0.048 | 0.499 (0.35) | 44.37 (5.59) | 0.282 | 0.878 (0.18) | 70.73 (8.16) |
| GI | Fa | 0.053 | 0.501 (0.26) | 44.41 (5.58) | 0.364 | 0.862 (0.11) | 70.21 (7.11) |
| UB | 44.40 (0.00) | 1 | 74.00 (0.00) | ||||