A meta-analysis is a statistical analysis that combines the results of multiple scientific studies. Meta-analyses can be performed when there are multiple scientific studies addressing the same question, with each individual study reporting measurements that are expected to have some degree of error. The aim then is to use approaches from statistics to derive a pooled estimate closest to the unknown common truth based on how this error is perceived. It is thus a basic methodology of Metascience. Meta-analytic results are considered the most trustworthy source of evidence by the evidence-based medicine literature.
|Part of a series on|
Not only can meta-analyses provide an estimate of the unknown effect size, it also has the capacity to contrast results from different studies and identify patterns among study results, sources of disagreement among those results, or other interesting relationships that may come to light with multiple studies.
However, there are some methodological problems with meta-analysis. If individual studies are systematically biased due to questionable research practices (e.g., data dredging, data peeking, dropping studies) or the publication bias at the journal level, the meta-analytic estimate of the overall treatment effect may not reflect the actual efficacy of a treatment. Meta-analysis has also been criticized for averaging differences among heterogeneous studies because these differences could potentially inform clinical decisions. For example, if there are two groups of patients experiencing different treatment effects studies in two randomised control trials (RCTs) reporting conflicting results, the meta-analytic average is representative of neither group, similarly to averaging the weight of apples and oranges, which is neither accurate for apples nor oranges. In performing a meta-analysis, an investigator must make choices which can affect the results, including deciding how to search for studies, selecting studies based on a set of objective criteria, dealing with incomplete data, analyzing the data, and accounting for or choosing not to account for publication bias. This makes meta-analysis malleable in the sense that these methodological choices made in completing a meta-analysis are not determined but may affect the results. For example, Wanous and colleagues examined four pairs of meta-analyses on the four topics of (a) job performance and satisfaction relationship, (b) realistic job previews, (c) correlates of role conflict and ambiguity, and (d) the job satisfaction and absenteeism relationship, and illustrated how various judgement calls made by the researchers produced different results.
Meta-analyses are often, but not always, important components of a systematic review procedure. For instance, a meta-analysis may be conducted on several clinical trials of a medical treatment, in an effort to obtain a better understanding of how well the treatment works. Here it is convenient to follow the terminology used by the Cochrane Collaboration, and use "meta-analysis" to refer to statistical methods of combining evidence, leaving other aspects of 'research synthesis' or 'evidence synthesis', such as combining information from qualitative studies, for the more general context of systematic reviews. A meta-analysis is a secondary source. In addition, meta-analysis may also be applied to a single study in cases where there are many cohorts which have not gone through identical selection criteria or to which the same investigational methodologies have not been applied to all in the same manner or under the same exacting conditions. Under these circumstances each cohort is treated as an individual study and meta-analysis is used to draw study-wide conclusions.