Clinical & Trials
Non-Inferiority Trial
In one line
A trial designed to demonstrate that a new intervention is not worse than an active comparator by more than a pre-specified, clinically acceptable margin.
Definition
A non-inferiority trial is designed to demonstrate that a new intervention is not unacceptably worse than an active comparator. The pre-specified non-inferiority margin (delta) defines the largest difference that would still be considered clinically acceptable; a one-sided 95% confidence interval that excludes a difference worse than the margin establishes non-inferiority. Common in MedTech when a placebo or sham control would be unethical (e.g., comparing a new drug-eluting stent against an established one).
Why it matters
Margin selection is the most contested element. FDA expects the margin to be both clinically defensible and to preserve a meaningful fraction of the comparator's effect over placebo (the 'M1/M2' framework).
Common pitfalls
- •Choosing a margin that's clinically defensible but doesn't preserve enough of the active comparator's effect — FDA will reject the design.
- •Running a non-inferiority trial with poor protocol adherence — drift biases toward the null and toward false NI conclusions.
Sources