|
Activity Number:
|
11
|
|
Type:
|
Invited
|
|
Date/Time:
|
Sunday, July 29, 2007 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
ASA, Utah Chapter
|
| Abstract - #308099 |
|
Title:
|
Responder versus Means Analysis: Illustrated with Data from a Phase 2 Study of Tarenflurbil (MPC-7869) in Alzheimer's Disease (AD)
|
|
Author(s):
|
Kenton Zavitz*+ and Mark Laughlin and Edward Swabb
|
|
Companies:
|
Myriad Pharmaceuticals and Myriad Pharmaceuticals and Myriad Pharmaceuticals
|
|
Address:
|
320 Wakara Way, Salt Lake City, UT, 84108,
|
|
Keywords:
|
Responder Analysis ; Power ; Clinical Trials ; Dementia ; Simulation Study
|
|
Abstract:
|
Preclinical data suggests a potential for MPC-7869---a Selective Aß42-Lowering Agent (SALA)---to have disease-modifying properties. In subjects with mild AD on 800 mg BID, statistical significance was observed for a means analysis at 12 and 24 months on the ADCS-ADL and the CDR-sb with positive trends on the ADAS-cog. Post-hoc responder analyses showed similar results. Responder analyses are often preferred by clinicians because they reflect a patient oriented approach, however, this analysis loses power by categorizing a continuum. Statisticians often prefer the potentially more sensitive means comparisons. In order to explore the statistical relationship between these two analysis approaches, data was simulated using four different distributions (a normal and a bimodal distribution each with 2 standard deviations) and the power and efficiency of these two approaches were compared.
|
- 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 2007 program |
