Analysing non-standard data and study designs


In analysing the outcomes of the studies included in your systematic review, you may encounter some more challenging types of data and study designs, including ordinal and time-to-event data, rates, cross-over trials, cluster randomised trials and more. The slidecast presentation provides a brief introduction to identifying and meta-analysing these outcomes.

The presentation has been translated into several languages other than English. Select an available language from the list at the top right of this page.

After using this resource, you should be able to...
  • Use the generic inverse variance method of meta-analysis
  • Identify and deal with non-standard data in studies included in a systematic review
  • Decide how to analyse studies with more than two groups
  • Identify and address unit-of-analysis issues in cluster-randomised and cross-over study designs

Analysing non-standard data and study designs - slidecast

Author information: 
Cumpston, Miranda

Approved by the Cochrane Methods Board on 23 September 2011.

Compiled by Miranda Cumpston, based on materials by Julian Higgins, Craig Ramsay, the Cochrane Statistical Methods Group and the Australasian Cochrane Centre