This research started as a joint effort by both authors. Unfortunately, the untimely death of Professor Lagakos did not allow him to contribute to the writing of the manuscript.
Statistical considerations when using a composite endpoint for comparing treatment groups
Article first published online: 1 AUG 2012
Copyright © 2012 John Wiley & Sons, Ltd.
Statistics in Medicine
Volume 32, Issue 5, pages 719–738, 28 February 2013
How to Cite
Gómez, G. and Lagakos, S. W. (2013), Statistical considerations when using a composite endpoint for comparing treatment groups. Statist. Med., 32: 719–738. doi: 10.1002/sim.5547
- Issue published online: 7 FEB 2013
- Article first published online: 1 AUG 2012
- Manuscript Accepted: 3 JUL 2012
- Manuscript Received: 28 DEC 2010
- National Institute of Allergy and Infectious Diseases. Grant Number: AI24643
- Ministerio de Ciencia y Tecnología, Spain. Grant Number: MTM2008-06747-C02-00
- asymptotic relative efficiency;
- clinical trials;
- combined outcomes;
- composite endpoints;
- log-rank test
When comparing two treatment groups in a time-to-event analysis, it is common to use a composite event consisting of two or more distinct outcomes. The goal of this paper is to develop a statistical methodology to derive efficiency guidelines for deciding whether to expand a study primary endpoint from (for example, non-fatal myocardial infarction and cardiovascular death) to the composite of and (for example, non-fatal myocardial infarction, cardiovascular death or revascularisation). We investigate this problem by considering the asymptotic relative efficiency of a log-rank test for comparing treatment groups with respect to a primary relevant endpoint versus the composite primary endpoint, say , of and , where is some additional endpoint. Copyright © 2012 John Wiley & Sons, Ltd.