Meta-Analysis

The meta-analysis research design involves analyzing many individual cases or research reports and looking for commonalities and discrepancies in the published findings. In this design, a group of previously researched cases is selected and subjected to comparative analysis. Gene V. Glass (1976) introduced the technique as a “rigorous alternative to the casual, narrative discussions of research studies which typify our attempts to make sense of the rapidly expanding research literature” (p. 3).

Meta-analysis is an observational technique used to summarize and compare the results of studies produced by other researchers. Objectives for meta case research include establishing the state of research findings on a subject and providing an overview of what others are saying about the subject. Referred to as an analysis of analyses, the method involves statistical analysis of a large collection of individual case studies for the purpose of integrating the findings of the total set. Below, the advantages and disadvantages of meta-analysis and the requisite steps are discussed in greater detail.

Meta-analyses should only be applied to empirical research reports—that is, studies that have analyzed primary quantitative data collected by researchers who prepared the original reports. The findings of previously prepared research reports are compared or evaluated using such statistical processes as regression and correlation analyses. A recent example of the design is the Chris Doucouliagos and Mehmet Ali Ulabaşoĝlu (2008) meta-analysis of 84 published studies of the hypothesized relationship between political democracy and economic growth. The individual results were spread across a continuum of positive, negative, and insignificant findings, leading them to conclude that while democracy does not have a direct impact on economic growth, an inconclusive relationship is common across the studies. Their meta-analysis resulted in three key points:

• 1.
  It provided a comprehensive analysis of the democracy–growth research based on the entire body of published cases.
• 2.
  Their quantitative analysis made it possible to make inferences based on the significance of the democracy–growth relationship.
• 3.
  It revealed the heterogeneity of the results in previous individual studies.