This site is not optimized for Internet Explorer 8 (or older).
Please upgrade to a newer version of Internet Explorer or use an alternate browser such as Chrome or Firefox.
Statistical Primer: Heterogeneity, Random- or Fixed-Effects Model Analyses?
Barili and colleagues discuss the importance of identifying heterogeneity in meta-analyses and the use of a random-effects or fixed-effects model to account for differences between or within studies. The authors review the assumptions and components of these models, discussing appropriate applications for each of them. Finally, they use an example analysis of surgical and transcatheter valve replacement outcomes to demonstrate the differences between random-effects and fixed-effects models.