|
Activity Number:
|
380
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 4, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #303466 |
|
Title:
|
Sample Size Re-Estimation for Poisson Distributed Variables with Partial Follow-Up
|
|
Author(s):
|
Jeannette Y. Lee*+ and Page C. Moore and Shelly Lensing
|
|
Companies:
|
University of Arkansas for Medical Sciences and University of Arkansas for Medical Sciences and University of Arkansas for Medical Sciences
|
|
Address:
|
4301 West Markham, #781, Little Rock, AR, 72205,
|
|
Keywords:
|
sample size ; poisson distribution ; clinical trial
|
|
Abstract:
|
Since sample size estimates for comparative clinical trials are based on previous studies with characteristics that vary from the proposed study, there is often an interest in sample size re-estimation based on preliminary study data. Variance estimates at the end of the study when the sample size has been re-estimated have been presented in the literature for normally distributed outcome measures. If the outcome measure is the rate of events per unit of time where participants are followed for a fixed period of time, and participants in the initial subset are followed for the entire period, variance estimates at the end of the study can be obtained through the normal approximation. We explore the implications for the variance estimates when sample size re-estimation is based on participants followed for a portion of the fixed period of time and the associated final test statistic.
|
