Non-Inferiority Trial

A clinical trial addresses a hypothesis.  If the hypothesis is that Drug A is at least as good as Drug B, then it is appropriate to set up the trial design and statistical plan to detect non-inferiority.  Drug A might be as good as Drug B  or it may even be better than Drug B.  Non-inferiority has the largest range of successful trial outcomes.  In other words, it is the easiest way to success and requires the smallest sample size.