|
Activity Number:
|
456
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Wednesday, August 1, 2007 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistical Graphics
|
| Abstract - #308344 |
|
Title:
|
Statistical and Graphical Analysis of Adverse Event Counts in Clinical Trials
|
|
Author(s):
|
Michael O'Connell*+
|
|
Companies:
|
Insightful Corporation
|
|
Address:
|
5317 Highgate Dr, Durham, NC, 27713,
|
|
Keywords:
|
|
|
Abstract:
|
Assessment of drug safety is a primary goal in drug development. However, in contrast to the design and analysis of efficacy endpoints, there is typically little planning or innovative statistical analysis of safety data. In particular, adverse events are usually reported as tables of counts for treatment and control, sometimes accompanied by results from a statistical test that is not well-suited to the data structure. In this talk we present some statistical and graphical analyses of adverse event data that address issues such as the sparse nature of the count data and the many adverse event terms under consideration. Statistical models considered include hierarchical generalized linear models, least angle regression and ensemble methods such as random forests. Results from these analyses are presented as S-PLUS® graphical summaries that highlight aspects of drug risks.
|
- 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 |
