JSM Preliminary Online Program
This is the preliminary program for the 2006 Joint Statistical Meetings in Seattle, Washington.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2006 Program page

Activity Number: 75
Type: Contributed
Date/Time: Sunday, August 6, 2006 : 4:00 PM to 5:50 PM
Sponsor: Biopharmaceutical Section
Abstract - #307397
Title: Can We Recruit Additional Subjects for a Failed Study?
Author(s): Paul Hshieh*+ and Tie-Hua Ng
Companies: U.S. Food and Drug Administration and U.S. Food and Drug Administration
Address: 1401 Rockville Pike, CBER, Rockville, MD, 20852-1448,
Keywords: unplanned interim analysis ; sample size ; binary outcomes
Abstract:

When a clinical trial fails to meet the study objective, but the results almost reach a statistical significance, it is tempting to recruit additional subjects in the hope that enlarging the study will result in a statistical significance. Such an action is operationally similar to performing an unplanned interim analysis; in general, it would lead to an inflation of the type I error rate and therefore, would be unacceptable. This problem always exists when evaluating continuous endpoints because the nominal alpha level is attained by the statistical tests. However, for discrete outcomes, such as the proportion of successes, the nominal alpha level is frequently not attained by the statistical tests. In such cases, the "leftover" alpha may be "spent" by the second analysis with additional subjects and the prespecified type I error rate is maintained. Examples will be given to illustrate

  • 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 2006 program

JSM 2006 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.
Revised April, 2006