Modified Haybittle–Peto group sequential designs for testing superiority and non-inferiority hypotheses in clinical trials

Abstract

In designing an active controlled clinical trial, one sometimes has to choose between a superiority objective (to demonstrate that a new treatment is more effective than an active control therapy) and a non-inferiority objective (to demonstrate that it is no worse than the active control within some pre-specified non-inferiority margin). It is often difficult to decide which study objective should be undertaken at the planning stage when one does not have actual data on the comparative advantage of the new treatment. By making use of recent advances in the theory of efficient group sequential tests, we show how this difficulty can be resolved by a flexible group sequential design that can adaptively choose between the superiority and non-inferiority objectives during interim analyses. While maintaining the type I error probability at a pre-specified level, the proposed test is shown to have power advantage and/or sample size saving over fixed sample size tests for either only superiority or non-inferiority, and over other group sequential designs in the literature.

Prehospital cooling to improve successful targeted temperature management after cardiac arrest: A randomized controlled trial

“…We planned to conduct 2 interim analyses after randomization of one-third (n = 300) and two-thirds (n = 600) of the total sample size. The trial could be stopped early for harm according to the early stopping criteria of Haybittle-Peto at a significance level of p < 0.001, for differences in either of the following 2 pre-specified endpoints: mortality during transport to hospital and survival with good neurological outcome at hospital discharge [26].…”

Adaptive designs for noninferiority trials

“…Further discussion of this interesting topic can be found in the concluding section of Mehta and Pocock () and Lai et al. ().…”

Benefits and harms of high-dose haemodiafiltration versus high-flux haemodialysis: the comparison of high-dose haemodiafiltration with high-flux haemodialysis (CONVINCE) trial protocol

“…Two formal interim analyses are planned using the Haybittle-Peto stopping criterion,44 45 but subject to the opinion of the DSMB. This states that we should stop the trial at any interim analysis where the absolute value of the estimated treatment effect is bigger than three times its SE.…”