Testing for heterogeneity among the components of a binary composite outcome in a clinical trial

<p>Abstract</p> <p>Background</p> <p>Investigators designing clinical trials often use composite outcomes to overcome many statistical issues. Trialists want to maximize power to show a statistically significant treatment effect and avoid inflation of Type I error rate...

Full description

Bibliographic Details
Main Authors: Devereaux PJ, Thabane Lehana, Pogue Janice, Yusuf Salim
Format: Article
Language:English
Published: BMC 2010-06-01
Series:BMC Medical Research Methodology
Online Access:http://www.biomedcentral.com/1471-2288/10/49
id doaj-520e23700b7c4f03934fc6ed76c52602
record_format Article
spelling doaj-520e23700b7c4f03934fc6ed76c526022020-11-24T20:54:16ZengBMCBMC Medical Research Methodology1471-22882010-06-011014910.1186/1471-2288-10-49Testing for heterogeneity among the components of a binary composite outcome in a clinical trialDevereaux PJThabane LehanaPogue JaniceYusuf Salim<p>Abstract</p> <p>Background</p> <p>Investigators designing clinical trials often use composite outcomes to overcome many statistical issues. Trialists want to maximize power to show a statistically significant treatment effect and avoid inflation of Type I error rate due to evaluation of multiple individual clinical outcomes. However, if the treatment effect is not similar among the components of this composite outcome, we are left not knowing how to interpret the treatment effect on the composite itself. Given significant heterogeneity among these components, a composite outcome may be judged as being invalid or un-interpretable for estimation of the treatment effect. This paper compares the power of different tests to detect heterogeneity of treatment effect across components of a composite binary outcome.</p> <p>Methods</p> <p>Simulations were done comparing four different models commonly used to analyze correlated binary data. These models included: logistic regression for ignoring correlation, logistic regression weighted by the intra cluster correlation coefficient, population average logistic regression using generalized estimating equations (GEE), and random effects logistic regression.</p> <p>Results</p> <p>We found that the population average model based on generalized estimating equations (GEE) had the greatest power across most scenarios. Adequate power to detect possible composite heterogeneity or variation between treatment effects of individual components of a composite outcome was seen when the power for detecting the main study treatment effect for the composite outcome was also reasonably high.</p> <p>Conclusions</p> <p>It is recommended that authors report tests of composite heterogeneity for composite outcomes and that this accompany the publication of the statistically significant results of the main effect on the composite along with individual components of composite outcomes.</p> http://www.biomedcentral.com/1471-2288/10/49
collection DOAJ
language English
format Article
sources DOAJ
author Devereaux PJ
Thabane Lehana
Pogue Janice
Yusuf Salim
spellingShingle Devereaux PJ
Thabane Lehana
Pogue Janice
Yusuf Salim
Testing for heterogeneity among the components of a binary composite outcome in a clinical trial
BMC Medical Research Methodology
author_facet Devereaux PJ
Thabane Lehana
Pogue Janice
Yusuf Salim
author_sort Devereaux PJ
title Testing for heterogeneity among the components of a binary composite outcome in a clinical trial
title_short Testing for heterogeneity among the components of a binary composite outcome in a clinical trial
title_full Testing for heterogeneity among the components of a binary composite outcome in a clinical trial
title_fullStr Testing for heterogeneity among the components of a binary composite outcome in a clinical trial
title_full_unstemmed Testing for heterogeneity among the components of a binary composite outcome in a clinical trial
title_sort testing for heterogeneity among the components of a binary composite outcome in a clinical trial
publisher BMC
series BMC Medical Research Methodology
issn 1471-2288
publishDate 2010-06-01
description <p>Abstract</p> <p>Background</p> <p>Investigators designing clinical trials often use composite outcomes to overcome many statistical issues. Trialists want to maximize power to show a statistically significant treatment effect and avoid inflation of Type I error rate due to evaluation of multiple individual clinical outcomes. However, if the treatment effect is not similar among the components of this composite outcome, we are left not knowing how to interpret the treatment effect on the composite itself. Given significant heterogeneity among these components, a composite outcome may be judged as being invalid or un-interpretable for estimation of the treatment effect. This paper compares the power of different tests to detect heterogeneity of treatment effect across components of a composite binary outcome.</p> <p>Methods</p> <p>Simulations were done comparing four different models commonly used to analyze correlated binary data. These models included: logistic regression for ignoring correlation, logistic regression weighted by the intra cluster correlation coefficient, population average logistic regression using generalized estimating equations (GEE), and random effects logistic regression.</p> <p>Results</p> <p>We found that the population average model based on generalized estimating equations (GEE) had the greatest power across most scenarios. Adequate power to detect possible composite heterogeneity or variation between treatment effects of individual components of a composite outcome was seen when the power for detecting the main study treatment effect for the composite outcome was also reasonably high.</p> <p>Conclusions</p> <p>It is recommended that authors report tests of composite heterogeneity for composite outcomes and that this accompany the publication of the statistically significant results of the main effect on the composite along with individual components of composite outcomes.</p>
url http://www.biomedcentral.com/1471-2288/10/49
work_keys_str_mv AT devereauxpj testingforheterogeneityamongthecomponentsofabinarycompositeoutcomeinaclinicaltrial
AT thabanelehana testingforheterogeneityamongthecomponentsofabinarycompositeoutcomeinaclinicaltrial
AT poguejanice testingforheterogeneityamongthecomponentsofabinarycompositeoutcomeinaclinicaltrial
AT yusufsalim testingforheterogeneityamongthecomponentsofabinarycompositeoutcomeinaclinicaltrial
_version_ 1716795078784057344