Elsevier

American Heart Journal

Volume 139, Issue 4, April 2000, Pages S171-S176
American Heart Journal

Proceedings of a symposium
Design and interpretation of equivalence trials

https://doi.org/10.1016/S0002-8703(00)90067-XGet rights and content

References (12)

There are more references available in the full text version of this article.

Cited by (65)

  • Prospects of Disease-Modifying Osteoarthritis Drugs

    2022, Clinics in Geriatric Medicine
  • The no-touch saphenous vein for coronary artery bypass grafting maintains a patency, after 16 years, comparable to the left internal thoracic artery: A randomized trial

    2015, Journal of Thoracic and Cardiovascular Surgery
    Citation Excerpt :

    For those predictor variables that did not fulfill the proportionality assumptions, stratified analyses were done. Comparisons with LITA: With the aim of investigating noninferiority and equivalence of the SV techniques with LITA, the approach recommended by Fleming19 and Christensen20 was used. Results are shown as confidence intervals (CI) for the differences in patency rates between the investigated techniques (LITA–SV).

  • The choice of the noninferiority margin in clinical trials was driven by baseline risk, type of primary outcome, and benefits of new treatment

    2015, Journal of Clinical Epidemiology
    Citation Excerpt :

    Noninferiority randomized trials are an increasingly popular study design, especially in the field of oncology, infectious diseases, or cardiovascular diseases [1,2]. The main purpose of such trials is to demonstrate that a new treatment is not substantially less effective than an existing treatment, while providing an additional advantage (in terms of convenience, burden of treatment, side effects, cost, and so forth.) [3]. A key challenge for such studies is to define what “not substantially less effective” means.

  • Does "not different" equal "the same"?

    2011, Annals of Emergency Medicine
    Citation Excerpt :

    In an equivalence trial, the null hypothesis is that the experimental treatment is either better or worse than the active comparator, with a treatment effect that falls outside the range of −Δ margin to +Δ margin. If the study produces a result that falls between the region −Δ to Δ, we reject the null hypothesis that 2 drugs differ, thereby implying that they may be the same.14-16,18-20 In a noninferiority trial, the null hypothesis is that the experimental treatment is worse than the alternative treatment by −Δ.

View all citing articles on Scopus
View full text