Two‐stage adaptive strategy for superiority and non‐inferiority hypotheses in active controlled clinical trials

Abstract

In active controlled trials without a placebo arm, there are usually two study objectives: to test a superiority hypothesis that the experimental treatment is more effective than the active control therapy, and to test a non-inferiority hypothesis that the experimental treatment is therapeutically no worse than the active control within a defined margin. For a two-stage adaptive design, it is not necessary to give a fixed sample size calculation at the planning stage of the study when treatment effect information is often insufficient. Instead, decision and estimation of the design specifications can be made more reliably after the first stage when interim results are available. We propose the use of conditional power approach to determine the sample size and critical values for testing the superiority and non-inferiority hypotheses for the second stage based on the observed result of the first stage. The proposed adaptive procedure preserves the overall type I error rate for both superiority and non-inferiority, and has the flexibility of early termination of the study (for futility or efficacy) or extending the study by appropriate sample size.

Randomized, phase 2 trial of low-dose cytarabine with or without volasertib in AML patients not suitable for induction therapy

“…The calculation of the phase 2 sample size was based on a stopping for futility approach, 23,24 assuming that the actual phase 2 trial represented an interim analysis of a (hypothetical) phase 3 trial. The test decision (with respect to phase 2) was made by looking at the conditional power that volasertib would show superiority in the hypothetical phase 3 trial.…”

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

“…Similar two-stage adaptive designs but with a less speciÿc procedure for determining the second-stage sample size were also considered by Brannath et al [16]. The focus of References [1,13,15,16] has been on how to maintain the overall type I error at a prescribed level in an adaptive design that allows mid-course switch between the superiority and noninferiority hypotheses. Although we have not mentioned it explicitly when we introduce our group sequential tests in Section 3, our goal has been to develop e cient tests that have the prescribed type I error probability.…”

“…Reference [9,Chapter 7], [14]). To circumvent the di culties for time-to-event endpoints in the group sequential approach with error spending functions, Shih et al [15] recently proposed to use a two-stage adaptive design instead of the more e cient group sequential strategy of Wang et al [1] for choosing between the superiority and non-inferiority objectives. Similar two-stage adaptive designs but with a less speciÿc procedure for determining the second-stage sample size were also considered by Brannath et al [16].…”

Estimation and Confidence Intervals for Two-Stage Sample-Size-Flexible Design with LSW Likelihood Approach

“…Shih et al [17] showed that when n 2 (u) is a non-increasing function of u, p(t, δ 0 ) expressed by (7) is an increasing function of δ 0 and also p(t, −∞) = 0 and p(t, ∞) = 1 for all finite t. Therefore, the lower bound of the (1 − α)100% one-sided C.I. can be found by solving the equation p(t, δ 0 ) = α.…”