Format

Send to

Choose Destination
See comment in PubMed Commons below
Am J Obstet Gynecol. 2007 Feb;196(2):119.e1-6.

Composite outcomes in randomized clinical trials: arguments for and against.

Author information

1
Department of Obstetrics and Gynaecology, University of Calgary, Calgary, Alberta, Canada.

Abstract

Composite outcomes that combine a number of individual outcomes (such as types of morbidity) are frequently used as primary outcomes in obstetrical trials. The main argument for their use is to ensure that trials can answer important clinical questions in a timely fashion, without needing huge sample sizes. Arguments against their use are that composite outcomes may be difficult to use and interpret, leading to errors in sample size estimation, possible contradictory trial results, and difficulty in interpreting findings. Such problems may reduce the credibility of the research, and may impact on the implementation of findings. Composite outcomes are an attractive solution to help to overcome the problem of limited available resources for clinical trials. However, future studies should carefully consider both the advantages and disadvantages before using composite outcomes. Rigorous development and reporting of composite outcomes is essential if the research is to be useful.

PMID:
17306647
DOI:
10.1016/j.ajog.2006.10.903
[Indexed for MEDLINE]
PubMed Commons home

PubMed Commons

0 comments
How to join PubMed Commons

    Supplemental Content

    Full text links

    Icon for Elsevier Science
    Loading ...
    Support Center