Skip to main content


Comparing multiple treatments 2: Statistical methods for network meta-analysis

Date and Location




Friday 20 September 2013 - 13:30 - 15:00


Methods Group and core training

Methods Group

Comparing Multiple Interventions Methods Group
Contact persons and facilitators

Contact person

Georgia Salanti


Georgia Salanti
Dimitris Mavridis
Anna Chaimani
Julian Higgins
Target audience

Target audience

review authors and statisticians

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


Objectives: To understand the statistical methodology of network meta-analyses and the assumption of consistency Description: This is the second out of two workshops on how to conduct Cochrane reviews that aim to compare more than two interventions and it is focused on statistical methodology for network meta-analysis. Network meta-analysis is the statistical methodology used to combine evidence in a network of trials that compare more than two interventions. The workshop will provide insight to network meta-analysis models that can be used to derive estimates for the relative effects of all treatments of interest. We will explore the different implementation alternatives through worked examples and we will discuss extensively the underlying assumption of consistency. We will present approaches to check for and incorporate inconsistency in the results and we will present applications of multiple-treatments meta-regression models. Finally, we will discuss concerns regarding the role of bias in network meta-analysis.