Critical interpretation of Cochran's Q test depends on power and prior assumptions about heterogeneity

Critical interpretation of Cochran's Q test depends on power and prior assumptions about heterogeneity

Autor Pereira, Tiago V. Autor UNIFESP Google Scholar
Patsopoulos, Nikolaos A. Google Scholar
Salanti, Georgia Google Scholar
Ioannidis, John P. A. Google Scholar
Instituição Universidade de São Paulo (USP)
Universidade Federal de São Paulo (UNIFESP)
Univ Ioannina
Harvard Univ
Fdn Res & Technol Hellas
Tufts Univ
Stanford Univ
Resumo We describe how an appropriate interpretation of the Q-test depends on its power to detect a given typical amount of between-study variance (tau(2)) as well as prior beliefs on heterogeneity. We illustrate these concepts in an evaluation of 1011 meta-analyses of clinical trials with >= 4 studies and binary outcomes. These concepts can be seen as an application of the Bayes theorem. Across the 1011 meta-analyses, power to detect typical heterogeneity was low in most situations. Thus, usually a non-significant Q test did not change perceptibly prior convictions on heterogeneity. Conversely, significant results for the Q test typically augmented considerably the probability of heterogeneity. the posterior probability of heterogeneity depends on what tau(2) we want to detect. With the same approach, one may also estimate the posterior probability for the presence of heterogeneity that is large enough to annul statistically significant summary effects; that is half the average within-study variance of the combined studies; and that is able to change the summary effect estimate of the meta-analysis by 20%. the discussed analyses are exploratory, and may depend heavily on prior assumptions when power for the Q-test is low. Statistical heterogeneity in meta-analyses should be cautiously interpreted considering the power to detect a specific tau(2) and prior assumptions about the presence of heterogeneity. Copyright (C) 2010 John Wiley & Sons, Ltd.
Palavra-chave heterogeneity
Q test
Bayes theorem
power analysis
meta-analysis
Idioma Inglês
Financiador Wood-Whelan research fellowship for a short-term visit at the Department of Hygiene and Epidemiology at the University of Ioannina
PENED training grant from the European Union Social Fund
Greek Ministry of Development, General Secretariat of Research and Technology
Data de publicação 2010-04-01
Publicado em Research Synthesis Methods. Hoboken: Wiley-Blackwell, v. 1, n. 2, p. 149-161, 2010.
ISSN 1759-2879 (Sherpa/Romeo, fator de impacto)
Publicador Wiley-Blackwell
Extensão 149-161
Fonte http://dx.doi.org/10.1002/jrsm.13
Direito de acesso Acesso restrito
Tipo Artigo
Web of Science WOS:000209380400005
Endereço permanente http://repositorio.unifesp.br/handle/11600/32400

Exibir registro completo




Arquivo

Arquivo Tamanho Formato Visualização

Não existem arquivos associados a este item.

Este item está nas seguintes coleções

Buscar


Navegar

Minha conta