Table 1 Bayesian adaptive designs explored for the Collaborative Ankle Support Trial
From: Bayesian adaptive designs for multi-arm trials: an orthopaedic case study
Design | Interim analysis schedulea | Arm allocation | Control allocation | Early stopping |
|---|---|---|---|---|
1 | None | 1:1:1:1 | Equal to other arms | None |
2 | Every 200 patients | 1:1:1:1 | Equal to other arms | Efficacy or futility every 200 patients |
3 | Every 50 patients | Arm dropping assessed at each interim analysis | Equal to other arms | Efficacy or futility every 200 patients |
4 | Every 50 patients | RAR at each analysis | Matched to best intervention arm | Efficacy or futility every 200 patients |
5 | Every 50 patients | RAR at each analysis | Fixed at 40% | Efficacy or futility every 200 patients |
6 | Every 50 patients | RAR at each analysis | No designated control; tubular bandage is treated as an intervention arm | Efficacy or futility every 200 patients |