Table 4 Expected mortality rates in whole trial for each randomisation method, given at point that the dexamethasone arm’s results were published
From: Should RECOVERY have used response adaptive randomisation? Evidence from a simulation study
Randomisation strategy | Average no. of deaths at n = 6400 +/− standard error (percentage) | Deaths prevented compared to FuR at n = 6400 |
|---|---|---|
FuR | 1583 +/− 1.1 (24.7%) | – |
FeR | 1556 +/− 1.0 (24.3%) | 27 |
Tf | 1528 +/− 1.2 (23.9%) | 55 |
RMCf | 1527 +/− 1.2 (23.9%) | 56 |
Ts | 1516 +/− 1.2 (23.7%) | 67 |
RMCs | 1514 +/− 1.2 (23.7%) | 69 |