The full content of Annals is available to subscribers

Subscribe/Learn More  >
Academia and the Profession |

Good Enough: A Primer on the Analysis and Interpretation of Noninferiority Trials

Sanjay Kaul, MD; and George A. Diamond, MD
[+] Article, Author, and Disclosure Information

From Cedars-Sinai Medical Center and David Geffen School of Medicine, University of California, Los Angeles, California.

Potential Financial Conflicts of Interest: None disclosed.

Requests for Single Reprints: Sanjay Kaul, MD, Division of Cardiology, Room 5536, South Tower, Cedars-Sinai Medical Center, 8700 Beverly Boulevard, Los Angeles, CA 90048; e-mail, kaul@cshs.org.

Current Author Addresses: Drs. Kaul and Diamond: Division of Cardiology, Room 5536, South Tower, Cedars-Sinai Medical Center, 8700 Beverly Boulevard, Los Angeles, CA 90048.

Ann Intern Med. 2006;145(1):62-69. doi:10.7326/0003-4819-145-1-200607040-00011
Text Size: A A A

Active-control noninferiority trials are being performed with increasing frequency when standard placebo-controlled trials are considered unethical. Three attributes are optimally required to establish noninferiority: 1) The treatment under consideration exhibits therapeutic noninferiority to the active control; 2) the treatment would exhibit therapeutic efficacy in a placebo-controlled trial if such a trial were to be performed; and 3) the treatment offers ancillary advantages in safety, tolerability, cost, or convenience. Trials designed to show noninferiority require an appropriate reference population, a proven active control and dose, a high level of adherence to treatment, and adequate statistical power. However, the formal analysis of such trials is founded on several assumptions that cannot be validated explicitly. These assumptions are evaluated in the context of 8 recently published noninferiority trials. The analyses in this paper confirm the establishment of noninferiority in only 4 of the 8 trials. The authors conclude that if noninferiority trials are to be applied to clinical and regulatory decisions about the marketing and use of new treatments, these assumptions must be made explicit and their influence on the resultant conclusions assessed rigorously.


Grahic Jump Location
Figure 1.
Basic concepts of noninferiority assessment.dotted line

The treatment effects are shown as 95% CIs around the estimates ( ). Criterion for success is defined as the 95% CI around the estimate of the new versus standard treatment, excluding the smallest expected effect (lower bound of the CI) of the standard treatment over placebo.

Grahic Jump Location
Grahic Jump Location
Figure 2.
Key steps in noninferiority assessment.Top.leftrightMiddle.dmax dleftrightPP(13)Bottom.(14)

Estimation of noninferiority margin is illustrated. The standard treatment (active control) effect is derived from analysis of 5 historical trials and is expressed as the absolute risk difference ( ) or the odds ratio for placebo relative to standard treatment ( ). Summary effects are estimated by using the DerSimonian–Laird method for random-effects meta-analysis. The CI comparison approach is illustrated, in which noninferiority is established when the upper bound of the 1-sided 97.5% CI (corresponding to a 2-sided 95% CI) lies within the noninferiority zone ( or ), represented by the shaded area. The analysis is shown for absolute risk difference ( ) and odds ratio ( ). Results of hypothesis testing are shown as values, with a 1-sided value less than or equal to 0.025 (corresponding to a 1-sided 97.5% CI) as the criterion for noninferiority . The putative placebo approach is shown in the left panel. The effect of the new treatment versus placebo, odds ratio, is derived from the effect of the new versus the standard treatment observed in the current trial and the effect of the standard treatment versus placebo in the historical trials. Superiority over putative placebo is established if the derived odds ratio for the new treatment versus placebo is less than 1.0. The fraction of standard treatment effect preserved by the new treatment using the Hasselblad and Kong method is shown in the right panel . Efficacy is established if the lower limit of the CI exceeds a target fractional threshold.

Grahic Jump Location




Citing articles are presented as examples only. In non-demo SCM6 implementation, integration with CrossRef’s "Cited By" API will populate this tab (http://www.crossref.org/citedby.html).


Submit a Comment/Letter
Submit a Comment/Letter

Summary for Patients

Clinical Slide Sets

Terms of Use

The In the Clinic® slide sets are owned and copyrighted by the American College of Physicians (ACP). All text, graphics, trademarks, and other intellectual property incorporated into the slide sets remain the sole and exclusive property of the ACP. The slide sets may be used only by the person who downloads or purchases them and only for the purpose of presenting them during not-for-profit educational activities. Users may incorporate the entire slide set or selected individual slides into their own teaching presentations but may not alter the content of the slides in any way or remove the ACP copyright notice. Users may make print copies for use as hand-outs for the audience the user is personally addressing but may not otherwise reproduce or distribute the slides by any means or media, including but not limited to sending them as e-mail attachments, posting them on Internet or Intranet sites, publishing them in meeting proceedings, or making them available for sale or distribution in any unauthorized form, without the express written permission of the ACP. Unauthorized use of the In the Clinic slide sets will constitute copyright infringement.


Buy Now for $32.00

to gain full access to the content and tools.

Want to Subscribe?

Learn more about subscription options

Related Articles
Topic Collections
Forgot your password?
Enter your username and email address. We'll send you a reminder to the email address on record.