|
Activity Number:
|
39
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Sunday, July 31, 2016 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biopharmaceutical Section
|
|
Abstract #321403
|
View Presentation
|
|
Title:
|
Sensitivity Analyses to Assess the Missing-at-Random Assumption
|
|
Author(s):
|
Shailaja Suryawanshi* and Anjela Tzontcheva and Raymond Lam and Gregory Golm
|
|
Companies:
|
Merck and Merck and Merck and Merck
|
|
Keywords:
|
Missing at random ;
MMRM ;
clinical trials
|
|
Abstract:
|
In Diabetes drug development the standard for assessment of efficacy is the change from baseline in A1C using a mixed-effects repeated measures (MMRM) model as the primary analysis approach. This analysis method produces valid inference as long as the mechanism underlying missingness is Missing at Random (MAR). Since it is not possible to test the validity of the MAR assumption, sensitivity analyses need to be conducted to assess the robustness of the primary conclusions to departures from MAR. Applications of one such sensitivity analysis based on the tipping point will be presented for both superiority and non-inferiority trials, and practical considerations arising from their implementation will be discussed.
|
Authors who are presenting talks have a * after their name.
