Abstract #300218

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 #300218
Activity Number: 6
Type: Invited
Date/Time: Sunday, August 3, 2003 : 2:00 PM to 3:50 PM
Sponsor: Section on Bayesian Stat. Sciences
Abstract - #300218
Title: ITT with Missing Outcomes via Multiple Imputation
Author(s): Donald B. Rubin*+
Companies: Harvard University
Address: 1 Oxford St., Cambridge, MA, 02138-2901,
Keywords:
Abstract:

The Intention To Treat principle states that inferences for causal effects in randomized experiments should compare groups of subjects according to how they were randomized. When there are missing outcomes, adherence to ITT requires the imputation of these missing outcomes, either implicit or explicit. One form of such impuations is to try to be wildly conservative with respect to the resultant p values. This approach is not only scientifically deceptive in general, but in particular situations can have effects opposite those intended, both statistical and ethical. As-treated analyses are generally not acceptable because they are based on generally implausible assumptions about the missing data being missing completely at random. Multiple imputation of the missing outcomes under scientifically plausible models is my preference, because valid inferences that adhere to ITT are accessible under explciit and often transparent assumptions. Two recent examples from FDA experience will be used to illustrate these ideas, one simple one involving a "device" and a second more complex one involving a rare genetic disorder.

  • 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