Online Program Home
My Program

Abstract Details

Activity Number: 254
Type: Contributed
Date/Time: Monday, August 1, 2016 : 2:00 PM to 3:50 PM
Sponsor: Biopharmaceutical Section
Abstract #321216 View Presentation
Title: Never Fit Sequence: The Design and Analysis of Multi-Period Clinical Trials
Author(s): Hans Hockey*
Companies: Biometrics Matters Ltd.
Keywords: multi-period ; cross-over ; sequence term ; linear model ; trial design ; confounding
Abstract:

Examples are given of the design and analysis of multi-period studies, typically cross-overs, in early phase studies in the pharmaceutical industry. The aim is to explore the usefulness of the inclusion of the between-subject sequence term typical in the linear models used for analysis and the effect this has on design. Starting with the simple two-period, two-treatment, two-sequence design, various multi-period studies are introduced and alternative designs and analyses considered. The usefulness for inference of different designs and analyses using models with and without sequence are contrasted. It is hoped to be able to show that omitting the sequence term from analysis models allows a broader range of designs, more useful models, and can give more information with the same experimental resources.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2016 program

 
 
Copyright © American Statistical Association