Issues in performing a network meta-analysis

  title={Issues in performing a network meta-analysis},
  author={Stephen J Senn and Françoise Gavini and David Magrez and Andr{\'e} Scheen},
  journal={Statistical Methods in Medical Research},
  pages={169 - 189}
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… 

Figures and Tables from this paper

GetReal in network meta‐analysis: a review of the methodology

This article presents a review of the relevant literature on NMA methodology aiming to pinpoint the developments that have appeared in the field.

The Impact of Performing a Network Meta-Analysis with Imperfect Evidence

This thesis investigates methods for dealing with imperfect evidence by considering two techniques for adjusting for confounding variables due to differing patient populations in a connected network and proposing a method for including single-arm evidence in a disconnected network through aggregate level matching.

Random main effects of treatment: A case study with a network meta‐analysis

It is illustrated how a hierarchical approach to modeling a random main effect of treatment can be used to produce shrunk (toward the overall mean) estimates of effects for individual treatments.

Statistical Models and Methods for Network Meta-Analysis.

The methods and models for conducting a network meta-analysis based on frequentist statistical principles are reviewed, and the procedures using a published multi-treatment plant pathology data set are demonstrated.

Visualizing the flow of evidence in network meta‐analysis and characterizing mixed treatment comparisons

A display of the flow of evidence and new measures that characterize the structure of a mixed treatment comparison are proposed and seen to render transparent the process of data pooling in mixed treatment comparisons in network meta-analysis.

Visualizing inconsistency in network meta-analysis by independent path decomposition

The approximation of the network estimate for a single comparison by the evidence of a subnet and the visualisation of the decomposition into independent paths provide the applicability of a graphical validation instrument that is known from classical meta-analysis.

A generalized pairwise modelling framework for network meta-analysis

A generalized pairwise modelling (GPM) framework for network meta-analysis, so named as it is based on the repeated application of adjusted indirect comparisons, also known as the Bucher method is introduced.

Network meta‐analysis and random walks

A novel analogy between NMA and random walks is presented and it is shown that the net number of times a walker crosses each edge of the network is related to the evidence flow network.

A graphical tool for locating inconsistency in network meta-analyses

The net heat plot is provided, to render transparent which direct comparisons drive each network estimate and to display hot spots of inconsistency, which permits singling out which of the suspicious direct comparisons are sufficient to explain the presence of inconsistency.

Using structural equation modeling for network meta-analysis

  • Y. TuY. Wu
  • Psychology
    BMC Medical Research Methodology
  • 2017
This article showed that a new approach to network meta-analysis based on the technique of unrestricted weighted least squares (UWLS) method can also be undertaken using SEM, and provided a very flexible framework for univariate and multivariate meta- analysis.



Graphical exploration of network meta-analysis data: the use of multidimensional scaling

Multidimensional scaling provides a useful tool for investigators to visualize the network of randomized comparisons and to assess incoherence of the network, without making any distributional assumptions.

Evaluation of networks of randomized trials

The concept of inconsistency and methods that have been proposed to evaluate it as well as the methodological gaps that remain are discussed and the implications of inconsistency, network geometry and asymmetry in informing the planning of future trials are discussed.

Network meta‐analysis for indirect treatment comparisons

  • T. Lumley
  • Psychology, Environmental Science
    Statistics in medicine
  • 2002
I present methods for assessing the relative effectiveness of two treatments when they have not been compared directly in a randomized trial but have each been compared to other treatments. These

The Many Modes of Meta

The options open to the meta-analyst in drug development are examined and comparisons to approaches used in analyzing multicenter trials are made in an attempt to provide some unifying insights, in particular as regards the handling of models with interactions.

Conducting indirect-treatment-comparison and network-meta-analysis studies: report of the ISPOR Task Force on Indirect Treatment Comparisons Good Research Practices: part 2.

Systematic Review: Why sources of heterogeneity in meta-analysis should be investigated

This paper distinguishes between the concepts of clinical and statistical heterogeneity and exemplifies the importance of investigating heterogeneity by using published meta-analyses of epidemiological studies of serum cholesterol concentration and clinical trials of its reduction.

Random-effects model for meta-analysis of clinical trials: an update.

Lessons from TGN1412 and TARGET: implications for observational studies and meta‐analysis

  • S. Senn
  • Psychology, Mathematics
    Pharmaceutical statistics
  • 2008
Two very different studies are examined: the first, a very large trial in osteoarthritis (the so‐called TARGET study) and the second a very small ‘first‐in‐man’ study of the monoclonal antibody

Statistical Methods for Comparison to Placebo in Active-Control Trials

This comparison addresses the issue of “drift” (the risk that a series of active-control trials might push the general therapy in the wrong direction by accepting therapies that are worse than previously approved therapy) using a generalization of the methodology described previously.