|
Activity Number:
|
342
|
|
Type:
|
Invited
|
|
Date/Time:
|
Wednesday, August 6, 2008 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
ENAR
|
| Abstract - #300175 |
|
Title:
|
Establishing Vaccine Safety in Studies with Rare Events
|
|
Author(s):
|
Valerii V. Fedorov*+
|
|
Companies:
|
GlaxoSmithKline
|
|
Address:
|
1250 S. Collegeville Rd, Collegeville, 19426,
|
|
Keywords:
|
vaccine safety study ; rare events ; early stopping
|
|
Abstract:
|
The primary goal of a vaccine safety trial is to assure that the vaccine is safe for the targeted population. Often that is done by rejecting the null hypothesis that the relative risk of an adverse event attributable to the new vaccine is above a given value, greater than one. The exact probability of type I error for the likelihood score test is evaluated by the straightforward enumeration of the binomial outcomes. The latter shows that the traditionally used normal approximation leads to sample sizes with type I error exceeding the nominal level. For rare adverse events, we recommend the Poisson approximation as a rather simple alternative and develop the conditional and unconditional tests. We also propose optimal randomization strategies which either minimize the total number of adverse cases or minimize the expected number of subjects when the vaccine is unsafe.
|
- 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 2008 program |
