Cargando…

A re-evaluation of random-effects meta-analysis

Meta-analysis in the presence of unexplained heterogeneity is frequently undertaken by using a random-effects model, in which the effects underlying different studies are assumed to be drawn from a normal distribution. Here we discuss the justification and interpretation of such models, by addressin...

Descripción completa

Detalles Bibliográficos
Autores principales: Higgins, Julian P T, Thompson, Simon G, Spiegelhalter, David J
Formato: Texto
Lenguaje:English
Publicado: Blackwell Publishing Ltd 2009
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2667312/
https://www.ncbi.nlm.nih.gov/pubmed/19381330
http://dx.doi.org/10.1111/j.1467-985X.2008.00552.x
_version_ 1782166113869627392
author Higgins, Julian P T
Thompson, Simon G
Spiegelhalter, David J
author_facet Higgins, Julian P T
Thompson, Simon G
Spiegelhalter, David J
author_sort Higgins, Julian P T
collection PubMed
description Meta-analysis in the presence of unexplained heterogeneity is frequently undertaken by using a random-effects model, in which the effects underlying different studies are assumed to be drawn from a normal distribution. Here we discuss the justification and interpretation of such models, by addressing in turn the aims of estimation, prediction and hypothesis testing. A particular issue that we consider is the distinction between inference on the mean of the random-effects distribution and inference on the whole distribution. We suggest that random-effects meta-analyses as currently conducted often fail to provide the key results, and we investigate the extent to which distribution-free, classical and Bayesian approaches can provide satisfactory methods. We conclude that the Bayesian approach has the advantage of naturally allowing for full uncertainty, especially for prediction. However, it is not without problems, including computational intensity and sensitivity to a priori judgements. We propose a simple prediction interval for classical meta-analysis and offer extensions to standard practice of Bayesian meta-analysis, making use of an example of studies of ‘set shifting’ ability in people with eating disorders.
format Text
id pubmed-2667312
institution National Center for Biotechnology Information
language English
publishDate 2009
publisher Blackwell Publishing Ltd
record_format MEDLINE/PubMed
spelling pubmed-26673122009-04-17 A re-evaluation of random-effects meta-analysis Higgins, Julian P T Thompson, Simon G Spiegelhalter, David J J R Stat Soc Ser A Stat Soc Original Articles Meta-analysis in the presence of unexplained heterogeneity is frequently undertaken by using a random-effects model, in which the effects underlying different studies are assumed to be drawn from a normal distribution. Here we discuss the justification and interpretation of such models, by addressing in turn the aims of estimation, prediction and hypothesis testing. A particular issue that we consider is the distinction between inference on the mean of the random-effects distribution and inference on the whole distribution. We suggest that random-effects meta-analyses as currently conducted often fail to provide the key results, and we investigate the extent to which distribution-free, classical and Bayesian approaches can provide satisfactory methods. We conclude that the Bayesian approach has the advantage of naturally allowing for full uncertainty, especially for prediction. However, it is not without problems, including computational intensity and sensitivity to a priori judgements. We propose a simple prediction interval for classical meta-analysis and offer extensions to standard practice of Bayesian meta-analysis, making use of an example of studies of ‘set shifting’ ability in people with eating disorders. Blackwell Publishing Ltd 2009-01 /pmc/articles/PMC2667312/ /pubmed/19381330 http://dx.doi.org/10.1111/j.1467-985X.2008.00552.x Text en © 2009 The Royal Statistical Society and Blackwell Publishing Ltd
spellingShingle Original Articles
Higgins, Julian P T
Thompson, Simon G
Spiegelhalter, David J
A re-evaluation of random-effects meta-analysis
title A re-evaluation of random-effects meta-analysis
title_full A re-evaluation of random-effects meta-analysis
title_fullStr A re-evaluation of random-effects meta-analysis
title_full_unstemmed A re-evaluation of random-effects meta-analysis
title_short A re-evaluation of random-effects meta-analysis
title_sort re-evaluation of random-effects meta-analysis
topic Original Articles
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2667312/
https://www.ncbi.nlm.nih.gov/pubmed/19381330
http://dx.doi.org/10.1111/j.1467-985X.2008.00552.x
work_keys_str_mv AT higginsjulianpt areevaluationofrandomeffectsmetaanalysis
AT thompsonsimong areevaluationofrandomeffectsmetaanalysis
AT spiegelhalterdavidj areevaluationofrandomeffectsmetaanalysis
AT higginsjulianpt reevaluationofrandomeffectsmetaanalysis
AT thompsonsimong reevaluationofrandomeffectsmetaanalysis
AT spiegelhalterdavidj reevaluationofrandomeffectsmetaanalysis