Analysis of Single-Arm Studies: Statistical Considerations of Study Site Variability from a Regulatory Perspective

• Activity Number: 620
• Type: Topic Contributed
• Date/Time: Thursday, August 5, 2010 : 8:30 AM to 10:20 AM
• Sponsor: Biopharmaceutical Section
• Author(s): Terri Kang Johnson*+ and Yunling Xu
• Companies: FDA/CDRH and FDA/CDRH
• Keywords: medical device ; single-arm ; poolability ; site variability ; regulatory perspective

Abstract

Often, trials to assess effectiveness and safety of medical devices are single-arm nonblinded studies. For devices that require surgeries in particular, blinding is not possible and randomizing a control to sham surgery is unethical. In analysis of such single-arm medical device studies, a "naïve" estimate of the mean and its variance without consideration of the site variability in study results are usually presented by sponsors. However, such mean estimate could be biased and its variance could be underestimated when significant site variability exits. In this paper, we'll discuss appropriate ways to handle site variability from a regulatory perspective and illustrate this with an example.