Skip to Main Content

Glossary

Meta-analysis

 

The literature about Systematic Reviews has a specific vocabulary. Here are some of the most common terms defined in the context of Systematic Reviews.

Bias - a systematic distortion of an estimated effect.

Heterogeneity- refers to the differences in the result sets generated in studies of the same subject, due to variations in the research parameters  used. This make it difficult to conduct a meta-analysis of the studies.

Homogeneity- refers to the similarities of the result sets generated in studies on the same subject, due to applying the same research parameters. This allows for a meta-analysis of multiple results sets to be conducted.

Many systematic reviews include a meta-analysisMeta-analysis uses statistical methods to combine the results of studies which address a same hypothesis, thus improving the validity of evidence.

Meta-synthesis is used for the synthesis of qualitative research. It "attempts to integrate results from a number of different but inter-related qualitative studies. Walsh, D., & Downe, S. (2005). Meta-synthesis method for qualitative research: A literature review. Journal of Advanced Nursing, 50(2), 204-211. doi: 10.1111/j.1365-2648.2005.03380.x

 Primary Studies- An original piece of research where the author generates new data by running a new experiment,  or  by collecting  original data from patients. Randomized Controlled Trials are examples of primary studies. In contrast a synthetic study does not generate new data, but combines results from several primary studies using meta-analysis or meta-synthesis.

Qualitative research - Research providing detailed narrative descriptions and explanations of phenomena investigated, with lesser emphasis given to numerical quantifications -- methods used to collect qualitative data include ethnographic practices such as observing and interviewing. ERIC thesaurus

Quantitative Research-Application of statistical processes and theory to the compilation, presentation, discussion, and interpretation of numerical data. ERIC thesaurus

Transparence - documentation of decisions taken around search strategy and study inclusion.