JSM 2004 - Toronto

Abstract #301260

This is the preliminary program for the 2004 Joint Statistical Meetings in Toronto, Canada. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 7-10, 2004); 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 2004 Program page
Activity Number: 439
Type: Contributed
Date/Time: Thursday, August 12, 2004 : 10:30 AM to 12:20 PM
Sponsor: Section on Statistics in Epidemiology
Abstract - #301260
Title: Alternative Analyses of Risk Factors for Composite Endpoints
Author(s): Robert J. Glynn*+ and Bernard A. Rosner
Companies: Brigham & Women's Hospital and Harvard Medical School
Address: 900 Commonwealth Ave., Boston, MA, 02215,
Keywords: polytomous regression ; competing risks ; survival analysis ; model building ; goodness-of-fit ; likelihood methods
Abstract:

Clinical trials and observational studies commonly consider composite endpoints, such as total mortality, all cancer or cardiovascular disease, to provide a broad evaluation of the benefits or risks of an intervention. Polytomous logistic regression and competing risk survival analysis offer alternative approaches to compare the overall and component-specific effects of risk factors and identify heterogeneity in these effects. We compared these approaches for evaluation of risk factors for a composite endpoint including myocardial infarction, stroke, and venous thromboembolism in a 20-year follow-up of 18,662 participants in the Physicians' Health Study. Strengths of both approaches include ready implementation in available software, likelihood-based strategies for comparing effects across components, interpretable parameters, and ability to include time-varying covariates. Polytomous logistic regression has the advantage of being fully parametric with accessible measures of goodness of fit and explained variance. Survival analysis better accounts for censoring and accommodates variables such as age that may have nonproportional effects on outcomes over time.

  • 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 2004 program

JSM 2004 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 March 2004