Inferiority Index and Margin Specification in One-Sided Equivalence Studies

• Activity Number: 485
• Type: Invited
• Date/Time: Wednesday, August 3, 2011 : 10:30 AM to 12:20 PM
• Sponsor: Statistics in Biopharmaceutical Research Journal
• Author(s): George Y. H. Chi*+ and Gang Li
• Companies: Johnson & Johnson Pharmaceutical R&D, LLC and Johnson & Johnson Pharmaceutical R&D, LLC
• Keywords: inferiority index ; margin ; degree of tightness ; non-inferiority trial ; comparative study

Abstract

In (one-sided) equivalence studies, the setting of an equivalence margin has often been controversial. This is true for example in non-inferiority trials. Much of the problems can be traced to a lack of an objective standard for measuring the stringency of a margin. In this presentation, we will introduce the concept of an inferiority index. It will be shown that under different types of distributions, the inferiority index can be linked to a given effect measure of interest. Through this link, the inferiority index can then provide a measure of the degree of tightness of a given margin for the effect measure. In addition, through this link, a margin can be specified with the desired level of stringency, although in practice, this should be done in conjunction with other relevant information. Its applications to non-inferiority trials will be illustrated with examples from survival, normal and Bernoulli distributions. Potential applications to other comparative studies will be noted.