Abstract #301549

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 #301549
Activity Number: 204
Type: Contributed
Date/Time: Tuesday, August 5, 2003 : 8:30 AM to 10:20 AM
Sponsor: Section on Bayesian Stat. Sciences
Abstract - #301549
Title: Likelihood Methods for Accounting for All-or-Nothing Treatment-Noncompliance and Subsequent Nonresponse in Randomized Trials
Author(s): Alistair James O'Malley*+ and Sharon-Lise Normand
Companies: Harvard University Medical School and Harvard University Medical School
Address: Dept. of Health Care Policy, Boston, MA, 02115-5821,
Keywords: causal inference ; EM algorithm ; instrumental variables ; likelihood function ; noncompliance ; nonresponse
Abstract:

Randomization is the backbone of clinical trial methodology. It is the medium through which causal inferences are made about the effect of treatment. When randomized trials are broken via noncompliance and nonresponse, analyses must account for these mechanisms. Recently, Frangakis and Rubin (1999) used method-of-moments to account for noncompliance and subsequent nonresponse. They assumed all-or-none compliance, and considered a problem when access to one of the treatments is restricted to those assigned that treatment. We will relax the second of these conditions. We consider parametric likelihood-based alternatives to Frangakis and Rubin's instrumental variables estimator (Frangakis and Rubin 1999). Marginal/integrated maximum likelihood (in which missing compliance states are averaged over), and maximum likelihood via the EM-algorithm, will be considered.

Our results indicate that the likelihood-based procedures perform significantly better than moment-based estimators. We also discuss the robustness of the new estimators to parametric assumptions.

  • 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