Comparison of Three Groups in the Gold Standard Non-Inferiority Design

Abstract

There are a number of situations where additional inclusion of a placebo arm in a non-inferiority trial is reasonable. Furthermore, proposals exist to decide when using placebo in clinical trials for methodological reasons is ethically justifiable. Due to the rich amount of information that can be gained, the three-arm design comparing placebo, the experimental treatment, and the reference is in the literature denoted as “gold standard” non-inferiority design. This chapter gives methods for sample size calculation for this design in case of normally distributed endpoints. Two different approaches are distinguished: the net effect approach, where assessment is based on the pairwise comparisons between placebo, the experimental treatment, and the reference, and the fraction effect approach, where non-inferiority assessment is based on effect retention of the experimental treatment versus the reference relative to placebo.