There are many methods available to fit random-effects meta-analysis. However, until 2024, the only option available in RevMan has been the DerSimonian and Laird random-effects method. This method is known to have poor statistical performance in meta-analyses with characteristics commonly found in Cochrane reviews (e.g., meta-analyses with few studies). To address this issue, Cochrane is implementing new random-effects methods in RevMan. These include a new method for estimating the between-study (heterogeneity) variance, calculating the confidence interval for the summary effect, and adding prediction intervals to aid in interpreting random-effects meta-analysis findings.
In two web clinics, the presenters provided participants with knowledge about these new methods and their implementation in RevMan. Specifically, in this first web clinic, the presenters outlined the new methods, while in the second clinic, they demonstrated the new methods using RevMan.
This first session covered the following:-
- Introduction to the new random-effects methods in RevMan
- Overview of methods to:-
- Estimate the heterogeneity variance (and its confidence interval).
- Calculate a confidence interval for the meta-analysis effect.
- Calculate a prediction interval. - Discussion on reasons for selecting a particular method.
- Interpretation of the estimates.
- Impact of the new methods on updating Cochrane Reviews.
- Guidance on what to write in a Cochrane protocol.
This first session was delivered in October 2024 and below you will find the videos from the webinar, together with the accompanying slides to download [PDF]. Recordings from other Methods Support Unit web clinics are available here.
Presenter Bios
Professor Jo McKenzie is head of the Methods in Evidence Synthesis Unit within the School of Public Health and Preventive Medicine at Monash University, Melbourne, Australia. She is Co-Convenor of the Cochrane Statistical Methods Group and an author of several chapters of the Cochrane Handbook for Systematic Reviews of Interventions.
Dr. Areti Angeliki Veroniki is a Scientist at the Knowledge Translation Program of the Li Ka Shing Knowledge Institute, St. Michael’s Hospital, Unity Health Toronto, and an Assistant Professor at the University of Toronto in the Institute of Health Policy, Management, and Evaluation. She is a Co-Convenor of the Cochrane Statistical Methods Group and Co-Chair of the Cochrane Methods Executive.
