Skip to main content

Table 5 Re-analysis over two stages of trials with final result showing evidence of a difference employing PFS as an intermediate outcome.

From: How do multi-stage, multi-arm trials compare to the traditional two-arm parallel group design – a reanalysis of 4 trials

  ICON4 RE01
one-sided sig. e I % ρ e I % ρ
level at stage 1   err.    err.  
0.5 75 0.04 0.27 53 3.18 0.27
0.4 97 0.20 0.29 69 4.58 0.31
0.3 125 0.03 0.36 88 1.08 0.34
0.2 162 0.26 0.39 114 0.26 0.39
0.1 221 0.12 0.44 155 0.46 0.46
  1. e I gives the number of control arm events for the significance level at stage 1, % err. gives the percentage of trials out of 5000 which were stopped, ρ gives the correlation between the test statistic at stage 1 on the intermediate outcome and at the final analysis on the primary outcome
\