Activity Number:
|
314
- Statistical Advancements in Neurodegeneration Trial Designs and Analyses
|
Type:
|
Topic Contributed
|
Date/Time:
|
Wednesday, August 5, 2020 : 10:00 AM to 11:50 PM
|
Sponsor:
|
Section for Statistical Programmers and Analysts
|
Abstract #312628
|
|
Title:
|
Impact of Model Misspecification on Alzheimer Trial Operating Characteristics
|
Author(s):
|
Saptarshi Chatterjee* and Shrabanti Chowdhury and Fanni Natanegara
|
Companies:
|
Eli Lilly and Co and Icahn school of Medicine at Mount Sinai and Eli Lilly and Company
|
Keywords:
|
Disease Progression;
Model Misspecification;
Alzheimer's Disease;
Mixed Effect Model
|
Abstract:
|
The trial designing stage usually involves methods that do not account for the longitudinal profile of the patients. The t-test statistic is a convenient choice to estimate sample size due to its simpler expression and ease of interpretation. However, in certain therapeutic areas such as Alzheimer’s disease (AD), the research interest often focuses on modeling the functional relationship of the overall disease progression of the treatment groups, where the mixed model repeated measures (MMRM) analysis is frequently used. In such situations, the t-test statistic provides a limiting option that underestimates the power considerably. The AD disease progression model (DPM) is another option to model the trajectory of patient response which provides additional flexibility of comparing participants by disease stage. The primary focus of this talk is to highlight the impact of model misspecification in the design and analysis stage on the operating characteristics of a clinical trial. A few simulation studies will be presented on both under-specification and over-specification of the analysis models to demonstrate the impact.
|
Authors who are presenting talks have a * after their name.