Issues in performing a network meta-analysis

Stephen Senn*, Francois Gavini, David Magrez, André Scheen

*Corresponding author for this work

Research output: Contribution to journalArticleResearchpeer-review

42 Citations (Scopus)

Abstract

The example of the analysis of a collection of trials in diabetes consisting of a sparsely connected network of 10 treatments is used to make some points about approaches to analysis. In particular various graphical and tabular presentations, both of the network and of the results are provided and the connection to the literature of incomplete blocks is made. It is clear from this example that is inappropriate to treat the main effect of trial as random and the implications of this for analysis are discussed. It is also argued that the generalisation from a classic random-effect meta-analysis to one applied to a network usually involves strong assumptions about the variance components involved. Despite this, it is concluded that such an analysis can be a useful way of exploring a set of trials.

Original languageEnglish
Pages (from-to)169-189
Number of pages21
JournalStatistical Methods in Medical Research
Volume22
Issue number2
DOIs
Publication statusPublished - Apr 2013

Keywords

  • Components of variance
  • incomplete blocks
  • indirect comparisons
  • mean-mean multiple comparisons plot

Fingerprint

Dive into the research topics of 'Issues in performing a network meta-analysis'. Together they form a unique fingerprint.

Cite this