Rare events are a common problem in Cochrane reviews, especially for secondary and safety outcomes. In the presence of rare events, standard meta-analytical models have important limitations and may lead to biased results.

The objective of this web clinic was to provide guidance on handling rare events in a Cochrane review, present the properties of the inverse variance method and explain why this method is problematic when outcome data are rare.

Afroditi explained the advantages of one-stage meta-analysis models over two-stage models and went through the assumptions and the properties of some of these models. 

Recording available here

Posted by Rachel Richardson