Meta-analysis

Background resources on systematic reviews and meta-analysis — start here if you are new to the topic.

What is a systematic review / meta-analysis?

An introduction to systematic reviews and meta-analysis, and how the two terms relate.

The steps involved in conducting a meta-analysis, from defining the research area to publishing the results.

Effect sizes, heterogeneity, moderators, and publication bias — with the underlying formulas.

Definitions of the most important terms used in meta-analysis.

Books and articles on meta-analysis, organized by topic.

Companion material for the steps above — multilevel models and reporting guidelines.

Handling dependent effect sizes when a study contributes more than one outcome, timepoint, or subscale.

How to read and fill in the PRISMA 2020 flow diagram, what changed from 2009, what the checklist covers, and the main extensions.

What each heterogeneity statistic tells you, and why I² alone is not enough.

There is no universal minimum: what the literature says about the smallest meta-analysis, power, heterogeneity, and moderators.

When to use each technique to explain heterogeneity, how to read the results, and the main pitfalls.

Extensions of the standard process above, relevant only for specific kinds of data or research questions.

Comparing three or more treatments at once by combining direct and indirect evidence, and the transitivity assumption it relies on.

Overlap-based effect sizes (PND, NAP, Tau-U) for single-subject A-B designs, where standard effect sizes don't apply.