Home  >>  Archives  >>  Volume 9 Number 1  >>  st0156

The Stata Journal
Volume 9 Number 1: pp. 40-56

Subscribe to the Stata Journal

Multivariate random-effects meta-analysis

Ian R. White
MRC Biostatistics Unit
Cambridge, UK
[email protected]
Abstract.   Multivariate meta-analysis combines estimates of several related parameters over several studies. These parameters can, for example, refer to multiple outcomes or comparisons between more than two groups. A new Stata command, mvmeta, performs maximum likelihood, restricted maximum likelihood, or method-of-moments estimation of random-effects multivariate meta-analysis models. A utility command, mvmeta_make, facilitates the preparation of summary datasets from more detailed data. The commands are illustrated with data from the Fibrinogen Studies Collaboration, a meta-analysis of observational studies; I estimate the shape of the association between a quantitative exposure and disease events by grouping the quantitative exposure into several categories.
Terms of use     View this article (PDF)

View all articles by this author: Ian R. White

View all articles with these keywords: mvmeta, mvmeta_make, mvmeta_l, meta-analysis, multivariate meta-analysis, individual participant data, observational studies

Download citation: BibTeX  RIS

Download citation and abstract: BibTeX  RIS