Format

Send to

Choose Destination
See comment in PubMed Commons below
Urol Oncol. 2008 May-Jun;26(3):320-9. doi: 10.1016/j.urolonc.2006.12.001. Epub 2007 Nov 7.

Meta-analysis in medical research: potentials and limitations.

Author information

1
Department of Social and Preventive Medicine, University of Berne, Berne, Switzerland. zwahlen@ispm.unibe.ch

Abstract

Meta-analysis, the statistical combination of results from several studies to produce a single estimate of a treatment effect or size of an association, continues to attract controversy. We illustrate and discuss the promises and limitations of meta-analysis. Meta-analysis of clinical trials can prevent delays in the introduction of effective treatments or lead to the timely identification of adverse effects. However, meta-analyses are liable to numerous biases, both at the level of the individual study and the selection of studies for inclusion in meta-analysis. The biases and confounding factors that threaten the validity of individual studies will also affect meta-analyses of observational studies. We argue that meta-analyses should only be performed within the framework of systematic reviews that have been prepared using methods that minimize bias and address the combinability of studies.

PMID:
18452828
DOI:
10.1016/j.urolonc.2006.12.001
[Indexed for MEDLINE]
PubMed Commons home

PubMed Commons

0 comments
How to join PubMed Commons

    Supplemental Content

    Full text links

    Icon for Elsevier Science
    Loading ...
    Support Center