Conflict of Interest Concerns in Medical Statistics

• Activity Number: 366
• Type: Invited
• Date/Time: Wednesday, August 1, 2007 : 8:30 AM to 10:20 AM
• Sponsor: Committee on Professional Ethics
• Author(s): Peter B. Imrey*+ and Saskia le Cessie*+ and Stephen Ruberg*+ and Lisa LaVange*+ and Susan S. Ellenberg*+ and Niels Keiding*+
• Companies: The Cleveland Clinic and Leiden University Medical Centre and Eli Lilly and Company and The University of North Carolina at Chapel Hill and University of Pennsylvania and University of Copenhagen
• Keywords: conflict of interest ; clinical trials ; data safety monitoring boards ; statistical ethics

Abstract

Medical research is under increasing scrutiny for conflicts-of-interest. With growing dependence of clinical research on private-sector support, suspicions have been heightened by notable instances of highly questionable research practices. Statistical issues are often central to disagreements about medical research design and analysis. Data from clinical studies are assembled and interpreted under statistical oversight, and statistical decisions may have pivotal influence on how studies are perceived. It seems inevitable that conflict-of-interest concerns encompass statistical work. A prominent journal conditions publication of industry studies on external academic replication of primary statistical results. How should the statistical profession view and respond to increasing alarm over potential conflicts of interest? Panelists with varying perspectives will review this problem.