A new approach to evaluating loop inconsistency in network meta-analysis


Network meta-analysis relies on an assumption of consistency, meaning that direct and indirect evidence should agree for each treatment comparison. Existing tests for inconsistency do not handle treatments symmetrically and global tests based on a design-by-treatment interaction approach lack power. In these videos, originally part of the Cochrane Learning Live webinar series, Becky Turner describes a new approach to evaluating inconsistency and demonstrates its application to three example networks.

The session consisted of a presentation followed by a Q&A and was aimed at statisticians with an interest in network meta-analysis. It was delivered in June 2022 and below you will find the videos from the webinar, together with accompanying slides to download [PDF].

Part 1: Introduction
Part 2: Identifying independent loops in a network
Part 3: Proposed inconsistency model
Part 4: Application to example networks
Part 5: Questions & answers


Presenter Bio

Becky Turner is a statistician based at the MRC Clinical Trials Unit at UCL in London, working on meta-analysis and trials methodology.


Part 1: Introduction


Part 2: Identifying independent loops in a network


Part 3: Proposed inconsistency model


Part 4: Application to example networks


Part 5: Questions & answers


Additional materials

Download the slides from the webinar [PDF].