• English
  • Español

Comparing multiple treatments 2: an introduction to network meta-analysis

Topic category Statistical methods and meta-analysis
Date and Location
Viernes 21 Octubre 2011 - 16:00 - 17:30
Methods Group
Methods Group: 
Comparing Multiple Interventions Methods Group
Contact person
Contact person: 
Deborah Caldwell (Contact this person)
NombreApellidoAffiliation and Country
Affiliation and Country: 
University of Bristol
Target audience
Target audience: 
Statisticians, Reviewers, Editorial teams
Is your workshop restricted to a specific audience or open to all Colloquium participants?: 
Level of knowledge required: 
Type of workshop
Type of workshop: 
Abstract text
To introduce the concepts and methodology of multiple treatment meta-analysis, a method which allows determination of the ‘best’ among a selection of interventions.

This is the second in a series of three workshops. The objective of multiple treatment meta-analysis (MTM) is to combine all the available trial evidence into an internally consistent set of estimates while respecting the randomisation in the evidence. An MTM provides estimates of the effect of each intervention relative to every other, whether or not they have been directly compared in trials. One can also calculate the probability that each treatment is the most effective. This workshop provides an introduction to the concepts and methodology of MTM within the context of an Overview. We will firstly describe the need for MTM and will then outline the potential benefits compared to conventional pair-wise meta-analysis, such as greater precision in summary estimates and ranking of treatments according to their effectiveness. We will use worked examples to explore the underlying assumptions necessary for MTM and will introduce the importance of checking for evidence consistency. A simple method for checking consistency in a three-treatment MTM will be outlined.