Estimands: discussion points from the PSI estimands and sensitivity expert group

• DOI: 10.1002/pst.1745
• Publication Date: 2016-03-21T15:25:07Z
• Authors: Alan Phillips; Juan Abellan‐Andres; Andersen Soren; Frank Bretz; Chrissie Fletcher; Lesley France; Andrew Garrett; Raymond Harris; Magnus Kjaer; Oliver Keene; David Morgan; Michael O'Kelly; James Roger
• Keywords: Addendum

ICH E9 Statistical Principles for Clinical Trials was issued in 1998. In October 2014, an addendum to proposed relating estimands and sensitivity analyses. preparation the release of addendum, Statisticians Pharmaceutical Industry held a 1‐day expert group meeting February 2015. Topics debated included definition, development, implementation, education communication challenges associated with The topic is important relatively new one clinical development. A clear message from that bridge gap between study objectives statistical methods. When defining estimands, iterative process linking trial objectives, design, analysis needs be established. Each objective should have at least distinct estimand, supported by Because trials are multi‐faceted expensive, it unrealistic restrict single estimand. actual set analyses will depend on disease setting various stakeholders. Copyright © 2016 John Wiley & Sons, Ltd.