Using an Estimand Approach in Your Next Clinical Trial

• Activity Number: 664 - Using an Estimand Approach in Your Next Clinical Trial
• Type: Topic Contributed
• Date/Time: Thursday, August 2, 2018 : 10:30 AM to 12:20 PM
• Sponsor: Biopharmaceutical Section
• Author(s): Frank Bretz* and Steven Gilbert* and Douglas S. Lee* and Jared Christensen* and Macaulay Okwuokenye*
• Companies: Novartis Pharma AG and Pfizer and Pfizer and Pfizer and Syros Pharmaceuticals Inc
• Keywords: Estimand; ICH; Clinical Trial; Pharmaceutical

Abstract

Estimands in clinical trials are a timely topic with the release of the ICH-E9: 'Addendum to Statistical Principles for Clinical Trials on Choosing Appropriate Estimands and Defining Sensitivity Analyses in Clinical Trials', which will affect long standing aspects of the design, documentation and analysis of clinical trials. The ICH estimand approach begins with the scientific objectives of the trial and proceeds to define the target of estimation (estimand), the estimator and finally the estimate itself; in theory providing a transparent path from study objectives to analysis methods. Many major pharmaceutical companies, such as Pfizer, have been preparing for these changes for over a year with statisticians leading the way, providing training and guidance. We will discuss estimands and their application in practice, sharing lessons learned; from acceptance by clinicians to changing analysis plans, that will greatly benefit statisticians working in clinical trials. This panel of experts will discuss the past, present and future of estimands in clinical trials putting them into a broader perspective and anticipating demands of the future.