Statistical heterogeneity: Notion and estimation in meta-analysis

Spineli, Loukia M.; Pandis, Nikolaos (2020). Statistical heterogeneity: Notion and estimation in meta-analysis. American journal of orthodontics and dentofacial orthopedics, 157(6), pp. 856-859. Elsevier 10.1016/j.ajodo.2020.03.009

Text j.ajodo.2020.03.009.pdf - Published Version Restricted to registered users only Available under License Publisher holds Copyright. Download (147kB) | Request a copy

The goal of a meta-analysis is not only to synthesize the information of selected studies, estimate the
summary effect size, and infer whether and how much the compared interventions differ in terms of their effectiveness but also to assess whether there is evidence of (statistical) heterogeneity in the true effect sizes, the magnitude of this heterogeneity, and its implications on the interpretation of the results. The term heterogeneity refers to the dispersion of the true effect sizes across the studies included in a meta-analysis.1 In this article, we address the importance of statistical heterogeneity,
and we present various tools that quantify the magnitude of heterogeneity and tools that signify the
presence of heterogeneity in a random-effects metaanalysis model, known as measures of heterogeneity. Statistical heterogeneity should not be confused with clinical heterogeneity, a related concept that refers to the heterogeneity of the included studies in terms of the characteristics of the included participants, the applied treatments, and the measured outcomes.

Interest & Impact

Downloads

2 since deposited on 24 Jun 2020
0 in the past 12 months

Citations

5 Citations in Web of Science ®
6 Citations in Scopus

Search

in Google Scholar™

Services

Actions (login required)

Edit item

Actions (login required)

Edit item