E-Mail karger@karger.com
Neuroepidemiology 2014;42:59–67
DOI: 10.1159/000355433
Advances in Meta-Analysis: Examples
from Internal Medicine to Neurology
Massimiliano Copetti
a
Andrea Fontana
a
Giusi Graziano
b, d
Federica Veneziani
e
Federica Siena
f
Marco Scardapane
c
Giuseppe Lucisano
c
Fabio Pellegrini
a, c
a
Unit of Biostatistics, Casa Sollievo della Sofferenza, San Giovanni Rotondo,
b
Laboratory of Lipid Metabolism and
Cancer, DTP, and
c
Unit of Biostatistics, DCPE, Consorzio Mario Negri Sud, Santa Maria Imbaro,
d
National Cancer
Research Center, IRCCS Oncologico Giovanni Paolo II,
e
Neurodegenerative Disease Unit, Department of Neurosciences
and Sense Organs, University of Bari, Bari, and
f
Department of Clinical and Research Neurology, Azienda Ospedaliera
Pia Fondazione Panico, Tricase, Italy
Background
Quite a long time has passed since the methodological
debate on uses and misuses of meta-analysis was domi-
nating the scene of research [1–4]. Either as a statistical
tool for combining evidence or as a methodological
framework, meta-analysis is now widely accepted. This
development, which occurred over the last decades, has
been impressive [5] (fig. 1) and primarily driven by the
needs of specific fields of research. We provide here a
thorough review of advances in the methodology of meta-
analysis, particularly stressing the clinical and research
needs which somehow determined them.
Biostatistics, in its essence as a ‘discourse on the meth-
od’, is always challenged by specific problems [6], and its
development often mirrors the necessity to solve practical
issues in science. It is broadly accepted that the first at-
tempt of meta-analysis goes back to 1904 when Karl Pear-
son was concerned with the pooling of existing evidence
in terms of a set of correlation coefficients obtained from
independent experiments [7].
Meta-analysis is a statistical technique to combine ev-
idence of different findings obtained by similar experi-
ments conducted on the same topic. When referring to a
finding, we usually intend a treatment or an intervention
effect on a given outcome. Logically this can be general-
ized to any form of exposure: risk factors, alleles, geno-
Key Words
Meta-analysis · Data pooling · Advanced techniques ·
Generalized linear mixed models · Exact methods · Bayesian
approaches
Abstract
Objective: We review the state of the art in meta-analysis and
data pooling following the evolution of the statistical models
employed. Methods: Starting from a classic definition of meta-
analysis of published data, a set of apparent antinomies which
characterized the development of the meta-analytic tools are
reconciled in dichotomies where the second term represents
a possible generalization of the first one. Particular attention
is given to the generalized linear mixed models as an overall
framework for meta-analysis. Bayesian meta-analysis is dis-
cussed as a further possibility of generalization for sensitivity
analysis and the use of priors as a data augmentation ap-
proach. Results: We provide relevant examples to underline
how the need for adequate methods to solve practical issues
in specific areas of research have guided the development of
advanced methods in meta-analysis. Conclusions: We show
how all the advances in meta-analysis naturally merge into the
unified framework of generalized linear mixed models and
reconcile apparently conflicting approaches. All these com-
plex models can be easily implemented with the standard
commercial software available. © 2013 S. Karger AG, Basel
Published online: December 12, 2013
Fabio Pellegrini
Consorzio Mario Negri Sud
Via Nazionale 8/A
IT–66030 Santa Maria Imbaro, Chieti (Italy)
E-Mail pellegrini @ negrisud.it
© 2013 S. Karger AG, Basel
0251–5350/14/0421–0059$39.50/0
www.karger.com/ned