|
Activity Number:
|
73
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Sunday, August 6, 2006 : 4:00 PM to 5:50 PM
|
|
Sponsor:
|
Biopharmaceutical Section
|
| Abstract - #306811 |
|
Title:
|
Three-Outcome Design for Randomized Comparative Phase II Clinical Trials
|
|
Author(s):
|
Shengyan Hong*+ and Yanping Wang
|
|
Companies:
|
Eli Lilly and Company and Eli Lilly and Company
|
|
Address:
|
Lilly Corporate Center, Indianapolis, IN, 46285,
|
|
Keywords:
|
randomized phase II trial ; three-outcome design ; statistical comparison ; two-stage design
|
|
Abstract:
|
Randomized design has been increasingly called for in oncology phase II trials to avoid patient selection bias in single arm design. However, formal statistical comparison is rarely conducted due to sample size restriction, despite its appealing feature. We offer an approach to sample size reduction by extending the three-outcome design of Sargent et al (2001) for single arm trials to randomized comparative trials. The design allows a third outcome: reject neither null nor alternative hypotheses when testing result is in "grey area". It could reduce sample size up to 30% over standard two-outcome design, making randomized comparative design an affordable option for Phase II clinical trials. The statistical formulation of three-outcome comparative design will be described and sample sizes for single-stage and Simon two-stage design will be tabulated.
|
