A More Powerful Test Based on Ratio Distribution for Retention Noninferiority Hypothesis

• Activity Number: 131
• Type: Contributed
• Date/Time: Monday, August 1, 2011 : 8:30 AM to 10:20 AM
• Sponsor: Biopharmaceutical Section
• Author(s): Ling Deng*+ and Gang Chen
• Companies: Johnson & Johnson Pharmaceutical R&D, LLC and Johnson & Johnson Pharmaceutical R&D, LLC
• Keywords: non-inferiority trial ; fraction retention ; ratio test ; ratio distribution ; synthesis method

Abstract

Rothmann et al. (Stat. Med. 2003; 22:239-264) proposed a method for the statistical inference of fraction retention non-inferiority (NI) hypothesis. A fraction retention hypothesis is defined as a ratio of the new treatment effect verse the control effect. One of the major concerns using this method is that with a limited sample size, the power of the study is usually very low. To improve power, Wang et al. (J. Biopharma. Stat. 2006; 16:151-164) proposed a ratio test based on asymptotic normality theory with a strong assumption of equal variance of the NI test statistic under null and alternative hypotheses in a sample size calculation. However, in practice, such assumption is generally questionable. This assumption is removed in the ratio test proposed in this paper, which is derived directly from a Cauchy-like ratio distribution. In addition, using this method, the fundamental assumption used in Rothmann's test, that the observed control effect is always positive, is no longer necessary. Without assuming equal variance under null and alternative hypotheses, the sample size can be significantly reduced if using the proposed ratio test for a fraction retention NI hypothesis.