Health & Environmental Research Online (HERO)


Print Feedback Export to File
5029248 
Book/Book Chapter 
Chapter 16: Statistical models for the meta-analysis of nonindependent data 
Jennions, MD; Jennions, MD; Schmid, CH 
2013 
Princeton University Press 
Princeton, NJ 
Handbook of Meta-analysis in Ecology and Evolution 
English 
is part of a larger document 5029185 Handbook of Meta-analysis in Ecology and Evolution
In many meta-analyses, independence is questionable because there are several effect estimates per study and/or some of the individual studies included in the meta-analysis might not provide independent estimates of the effect. Within-study nonindependence can arise due to multiple measures of the same effect on the same experimental units being made over time, multiple treatments being compared to the same set of control individuals, or different measures being taken (e.g., plant height, dry weight, and photosynthesis rate) from the same experimental units to generate several different effect size estimates. This chapter discusses nonindependence among effect sizes both within and among studies. It focuses on four commonplace situations where nonindependence can occur in ecology and evolution meta-analyses. Each of these four situations is illustrated with a single case study.