Portal de Periódicos da CAPES

On non-inferiority margin and statistical tests in active control trials

2005; Wiley; Volume: 25; Issue: 7 Linguagem: Inglês

10.1002/sim.2208

1097-0258

Shein‐Chung Chow, Jun Shao,

Statistical Methods and Bayesian Inference

The problem of selecting a non-inferiority margin and the corresponding statistical test for non-inferiority in active control trials is considered. For selection of non-inferiority margin, the guideline by the International Conference on Harmonization (ICH) recommends that the non-inferiority margin should be chosen in such a way that if the non-inferiority of the test therapy to the active control agent is claimed, the test therapy is not only non-inferior to the active control agent, but also superior to the placebo. Furthermore, variability should be taken into account. Along this line, a method for selecting non-inferiority margins with some statistical justification is proposed. Statistical tests for non-inferiority designed in the situation where the non-inferiority margin is an unknown parameter are derived. An example concerning a cancer trail for testing non-inferiority with the primary study endpoint of the time to disease progression is presented to illustrate the proposed method.