The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Abstract Details
Activity Number:
|
14
|
Type:
|
Topic Contributed
|
Date/Time:
|
Sunday, July 31, 2011 : 2:00 PM to 3:50 PM
|
Sponsor:
|
International Chinese Statistical Association
|
Abstract - #302466 |
Title:
|
Reassessing Study Power and Sample Size of an Ongoing Trial Without Breaking the Blind
|
Author(s):
|
Biao Xing*+
|
Companies:
|
sanofi-aventis
|
Address:
|
270 Albany St, Cambridge, MA, 02139,
|
Keywords:
|
sample size ;
adaptive design ;
randomized trial ;
blinding
|
Abstract:
|
Planning an appropriate sample size of a pivotal trial is important to a drug development program because the sponsor may miss a potential drug if the sample size is too small or have an inefficient (and sometimes unethical) trial if the sample size is too big. When the assumptions used for sizing the trial are shaky, it is desirable to re-assess the power and the sample size while the trial is on-going. We developed a method for re-estimating the sample size of a randomized blind trial with a continuous endpoint without breaking the blind. The main idea is to estimate the variance based on the randomization block sums. The proposed method is unbiased, simple to use and can be used for a wide set of designs. Effects of covariates can be adjusted. Our blinded estimation method poses no risk of comprising the integrity of the study and it almost causes no inflation in the Type I error rate. When weighing the burden imposed by interim unblinded re-estimation against the loss in precision with blinded re-estimation, our method is advantageous for some trials.
|
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 2011 program
|
2011 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Continuing Education program, please contact the Education Department.