[Methodological and statistical aspects of equivalence and non inferiority trials]

Abstract

Background: - The existence of effective reference treatments means that the superior therapeutic efficacy of new treatments is less marked and thus more difficult to demonstrate statistically. Moreover, the potential value of a new treatment is also based on other criteria, such as costs, ease of use, non invasiveness, and immediate or long-term side effects. In this context, methodological issue becomes one of looking for equivalence or non inferiority of the new treatment in comparison with an existing, high-performance reference treatment.

Methods: - In the present work, we reexamine the statistical rational and methodological features of equivalence and non inferiority trials.

Results: - We address equivalence margin choice, hypotheses building, and the different approaches for establishing equivalence (hypothesis testing and confidence intervals). We then discuss key aspects of equivalence trial design and the important methodological quality criteria involved in performing such studies: choice of the reference treatment, subject eligibility criteria, primary endpoint, study population and the required sample size. Lastly, we consider the possibility of adopting a new analytical strategy (non inferiority/superiority).

Conclusion: - A checklist of items to include when reporting the results of randomized controlled trials (Consolidated Standards of Reporting Trials, the CONSORT recommendations) has been adapted for use in non inferiority and equivalence randomized controlled trials.