|
Activity Number:
|
97
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Monday, August 7, 2006 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
ENAR
|
| Abstract - #305904 |
|
Title:
|
Evaluation of Treatment-Country Interaction in Global Clinical Trials
|
|
Author(s):
|
Hajime Uno*+ and Yoshiharu Horie and Masahiro Takeuchi
|
|
Companies:
|
Kitasato University and Nippon Boehringer Ingelheim Co., Ltd. and Kitasato University
|
|
Address:
|
60 Babcock Street, BROOKLINE, MA, 02446,
|
|
Keywords:
|
global clinical trial ; prediction model
|
|
Abstract:
|
When making inferences for the treatment effect as a global measure in a global clinical trial, it is important to evaluate the presence of the treatment-country interaction. A popular way to do this is through a significance test; however, this may not be appropriate. We propose an approach to evaluate the treatment-country interaction in terms of prediction accuracy measures for future patients' outcome. Applying a large sample theory for prediction accuracy measures, we report point and interval estimates of those measures to see how much the treatment-country interaction can improve the prediction of the future patients' outcome in participating countries. We illustrate this approach using real data from a global clinical trial.
|
