Abstract #301217

This is the preliminary program for the 2003 Joint Statistical Meetings in San Francisco, California. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 2-5, 2003); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.

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 2003 Program page
JSM 2003 Abstract #301217
Activity Number: 421
Type: Contributed
Date/Time: Wednesday, August 6, 2003 : 2:00 PM to 3:50 PM
Sponsor: Biopharmaceutical Section
Abstract - #301217
Title: Regression to the Mean in HIV Clinical Trials
Author(s): Michael L. Nessly*+ and Y. H. Josh Chen
Companies: Merck & Co., Inc. and Merck Research Laboratories
Address: PO Box 4, West Point, PA, 19486-0004,
Keywords: regression to mean ; surrogate endpoints ; bias ; clinical trials ; restricted randomization ; truncation
Abstract:

Baseline virological and immunological markers are strong predictors of outcomes in HIV clinical trials. These measurements are highly variable in both major components of variability (intrinsic biological variability and measurement error) and are particularly variable at the extremes of the assay dynamic range. When these markers are utilized either as entry criteria or as a randomization blocking factors, then results are subject to regression to the mean. The magnitude of this bias is determined by the replicate variability of the assays, the proximity of the distribution of values to the limits imposed and the correlations between the measurements. Laboratory markers are used in many designs to define the target population, restrict the randomization and as the primary efficacy variable. While change from baseline may be based upon post-screening values, it is generally the restricted screening values that comprise the basis of restricted randomization. Therefore, to analyze as randomized one must risk of regression to the mean bias. We show simulations and examples based on actual study data of the existence, magnitude and direction of regression to the mean.

  • 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 2003 program

JSM 2003 For information, contact meetings@amstat.org or phone (703) 684-1221. If you have questions about the Continuing Education program, please contact the Education Department.
Revised March 2003