Back to Agendas
Session 3: Estimands and Sensitivity Analyses
Session Chair(s)
Feng Li
Lead Mathematical Statistician
FDA/CDER, United States
Frank Bretz, PhD
Distinguished Quantitative Research Scientist
Novartis , Switzerland
Defining the primary objective of a clinical trial in the presence of non-compliance or non-adherence to the assigned treatment is crucial for the choice of design, the statistical analysis and the interpretation of the results. This raises the need for a structured framework to specify the primary estimand (i.e. "what is to be estimated"). The missing data report released in 2010 by the National Academy of Science, “Prevention and Treatment of Missing Data in Clinical Trials”, recommends explicit specification of a casual estimand in the protocol of a confirmatory trial. This is also reflected by the decision of ICH to amend its E9 guidance in the coming years to discuss estimands and their role in clinical trials. In this session we will discuss a clear definition of estimands and how the choice of an estimand is linked to important considerations around trial design, conduct and analysis.
Speaker(s)
Framework for Estimands
Mouna Akacha, PhD
Novartis Pharma AG, Switzerland
Group Head of Statistical Methodology
Case Study
Bradley McEvoy
FDA, United States
Mathematical Statistician, Division of Biometrics II, OBS, OTS, CDER
Panelists (joining the Speakers)
Thomas J. Permutt, PhD
FDA, United States
Associate Director for Statistical Science and Policy, OB, OTS, CDER
Christine Fletcher, MSc
GlaxoSmithKline, United Kingdom
VP/Head, Speciality and Primary Care Statistics
Stephen Ruberg, PhD, MS
Analytix Thinking, United States
President; Adjunct Professor of Statistics, Purdue University
Daniel O. Scharfstein
Johns Hopkins University, United States
Associate Professor of Biostatistics
Have an account?