|
Activity Number:
|
291
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 14, 2002 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Biopharmaceutical Section*
|
| Abstract - #301536 |
|
Title:
|
Non-Stop Drug Development: Statistical Methods for More Time Efficient Trials
|
|
Author(s):
|
Karen Kesler*+ and Russell Helms
|
|
Affiliation(s):
|
Rho, Inc. and Rho, Inc.
|
|
Address:
|
100 Eastowne Dr., Chapel Hill, North Carolina, 27514, USA
|
|
Keywords:
|
group sequential ; clinical trial ; futility boundaries
|
|
Abstract:
|
The traditional strategy for drug development Phases II through III is to plan a series of studies, each of which has a small number of relatively specific objectives. Recent advances in statistical methods, especially in the area of group sequential analysis, may lead to more time efficient strategies. For example, instead of performing multiple Phase II studies followed by two Phase III studies, it may be possible to design two larger studies that encompass both Phase II and Phase III. The studies would include a number of intermediate analyses that would permit "pruning" unproductive arms of a study to intensify the focus on productuve arms and objectives. We will explore the adjustments to standard group sequential analyses this new paradigm would require, including changes to the efficacy boundaries to control for the increase in treatment arm comparisons, as well as choosing appropriate futility boundaries. We will also discuss the potential statistical impact of logistic issues to this new design.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2002 program |
