Journal of clinical epidemiology
-
Research review has long been one of the most important scholarly activities in all branches of science. While there is sometimes a single study so well-designed, well carried out, and difficult to replicate that its findings are accepted as conclusive, more often there are many studies on a given topic, no one of which clearly supersedes the others. ⋯ They may arrive at different conclusions. When this is the case, there is a need for reviewers to carefully consider the evidence and to put forth conclusions or hypotheses about where the weight of the evidence lies.
-
Meta-analysis has been defined as a study and "statistical analysis which combines or integrates the results of several independent studies." Included in this definition are other terms, such as systematic overviews, pooling data, pooling study results, and quantitative literature reviews. Like any study, the questions being asked will influence the design and the method of analysis of the meta-analysis. Since a meta-analysis is a study based on a literature review, it is inherently observational rather than experimental in nature. ⋯ In this second type of meta-analysis the characteristics of the different studies become the focus of the analysis. This leads to the idea that protocols for a meta-analysis should reflect its goals and how the results are to be used. Finally, we will consider whether there is a role of meta-analysis in the field of drug development.
-
The paper discusses some of the most common criticisms to meta-analysis presented by Professor Feinstein in this Conference. As many of the points raised in his contributions are not new, a critique to them is presented in the context of the type of contribution given by systematic reviews (meta-analysis) to the analysis of the effects of health care interventions. After discussing some terminological issues, the paper challenges Feinsteins' arguments indicating that meta-analysis is inherently faulted on four grounds: (a) reproducibility, (b) precision, (c) suitable extrapolation, (d) fair comparison. Each point is discussed providing examples drawn from the published literature with a view to indicate that--despite their current limitations--systematic reviews are a necessary step to synthesize information, orient clinical research and help produce practice guidelines.