|
Activity Number:
|
92
|
|
Type:
|
Invited
|
|
Date/Time:
|
Monday, August 7, 2006 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #304959 |
|
Title:
|
Accounting for Variability in Sample Size Estimation with Application to a Malaria Vaccine Phase II Trial
|
|
Author(s):
|
Michael P. Fay*+ and M. Elizabeth Halloran and Dean A. Follmann
|
|
Companies:
|
National Institute of Allergy and Infectious Diseases and Fred Hutchinson Cancer Research Center and National Institute of Allergy and Infectious Diseases
|
|
Address:
|
6700B Rockledge Drive, MSC 7609, Bethesda, MD, 20892-7609,
|
|
Keywords:
|
sample size ; binomial ; compliance ; Poisson ; normal ; variability
|
|
Abstract:
|
We use data from a longitudinal study in Mali to study several possible endpoints for designing a Phase 2 vaccine trial for a Malaria vaccine. We assume the differences in endpoints between 4-year-old control subjects and 4-year-old vaccinated subjects are similar to observed differences between nonvaccinated 4 and 8 year olds. Because there are fewer than 50 children within one year of each age group in the preliminary data, there is considerable variability in the resulting sample size estimates. We develop a general method for adjusting the sample size estimates to account for this variability so the final sample size estimates have the proper power, assuming only that the preminary data and the planned study follow the same probability model. In addition, we adjust the sample sizes to account for the case when only a proportion of vaccinated subjects respond to the vaccine.
|
