Pairwise meta-analysis (PW-MA) is a method that pools evidence from randomised controlled trials (RCTs) that compare the same two interventions. Network meta-analysis (NMA) extends this to multiple interventions, where each RCT compares two or more different interventions. NMA allows one to simultaneously estimate relative effectiveness for any pair of interventions forming an evidence network. The validity of the methods rest on the assumption of exchangeability of study effects both within and between intervention contrasts. It is therefore important to test for and investigate causes of heterogeneity, and for NMA whether this depends on intervention contrast (known as inconsistency). The aim of this course is to introduce pairwise and network meta-analysis, including exploration of heterogeneity and inconsistency.

Learning Objectives
By the end of the course participants should be able to:

  • understand the need for systematic reviews and (network) meta-analysis
  • understand the difference between “fixed effect” and “random effects” pairwise meta-analysis models
  • be able to interpret the output from a pairwise meta-analysis
  • be aware of possible causes of heterogeneity and methods to test for this
  • understand how subgroup analyses and meta-regression can be used to explore heterogeneity, and acknowledge the limitations of these methods
  • understand what indirect comparisons and network meta-analysis (NMA) and understand the difference between the “fixed effect” and “random effects” network meta-analysis models
  • be able to interpret the output from a network meta-analysis
  • be aware of different techniques to present and use the results from NMA
  • understand the assumptions made in NMA, and different methods to test for inconsistency
  • understand how meta-regression and subgroup analyses can be applied in NMA
  • identify appropriate likelihood and link functions for different outcome measure types, in a generalised linear modelling framework.

Who is this course for?
This course is designed for epidemiologists, statisticians, and decision analysts. It is assumed that participants are familiar with linear and logistic regression.

Location: Room 00.34/00.46, Joris Helleputte, Minderbroedersstraat 8, 3000 Leuven

I-Biostat member: 50 Euro
Student: 150 Euro
Academic member: 250 Euro
Non-academic member: 500 Euro
Note: ISCB members (not: I-Biostat members or students) are entitled to a 50 Euro reduction upon showing a valid proof of their ISCB membership.

To register: go to
Additional practical information can be obtained from Kirsten Verhaegen at L-Biostat (

Announcement course MA and NMA Nicky Welton 2018