CoChat

Evidence Synthesis for Decision Making 2: A Generalized Linear Modeling Framework for Pairwise and Network Meta-analysis of Randomized Controlled Trials

Open access
Dias, Sofia, Sutton, Alex J., Ades, A. E., Welton, Nicky J. · 2013 · Medical Decision Making

The DOI matches its Crossref record; 96 of the 96 references it cites were found in a registry or an index; none of the 13 sources its claims cite is checked for support yet.

Abstract

We set out a generalized linear model framework for the synthesis of data from randomized controlled trials. A common model is described, taking the form of a linear regression for both fixed and random effects synthesis, which can be implemented with normal, binomial, Poisson, and multinomial data. The familiar logistic model for meta-analysis with binomial data is a generalized linear model with a logit link function, which is appropriate for probability outcomes. The same linear regression framework can be applied to continuous outcomes, rate models, competing risks, or ordered category outcomes by using other link functions, such as identity, log, complementary log-log, and probit link functions. The common core model for the linear predictor can be applied to pairwise meta-analysis, indirect comparisons, synthesis of multiarm trials, and mixed treatment comparisons, also known as network meta-analysis, without distinction. We take a Bayesian approach to estimation and provide WinBUGS program code for a Bayesian analysis using Markov chain Monte Carlo simulation. An advantage of this approach is that it is straightforward to extend to shared parameter models where different randomized controlled trials report outcomes in different formats but from a common underlying model. Use of the generalized linear model framework allows us to present a unified account of how models can be compared using the deviance information criterion and how goodness of fit can be assessed using the residual deviance. The approach is illustrated through a range of worked examples for commonly encountered evidence formats.

Overview

CoChat Summary

## TL;DR

This paper presents a unified Bayesian generalized linear model framework for evidence synthesis of aggregate randomized trial data, covering pairwise meta-analysis, multiarm trials, indirect comparisons, and network meta-analysis. It shows how different outcome types can be handled with appropriate likelihoods and link functions, and how model fit can be assessed with residual deviance and DIC.

## Key findings

  • The framework covers normal, binomial, Poisson, and multinomial likelihoods with identity, logit, log, complementary log-log, and probit links, all within a common core linear predictor.
  • In the worked example of 22 trials of beta-blockers after myocardial infarction, the fixed-effect model gave a posterior median pooled log odds ratio of −0.26 with 95% CrI (−0.36, −0.16), and posterior median mortality probabilities of 0.10 in control and 0.08 in treatment.
  • For that example, the random-effects model fit better by residual deviance, with D̄res = 41.9 versus 46.8 for the fixed-effect model, but the paper says the DIC suggested little to choose between them.
  • The paper states that the same model structure can synthesize pairwise meta-analysis, indirect comparisons, multiarm trials, and network meta-analysis “without distinction.”

## Methods

  • The paper develops a Bayesian MCMC approach to evidence synthesis, implemented in WinBUGS 1.4.3, with annotated code provided in a web appendix.
  • It presents a generalized linear model (GLM) formulation for aggregate trial data, using a common linear predictor with fixed-effect and random-effects versions.
  • An illustrative meta-analysis of 22 beta-blocker trials is used for the binomial/logit example, and model fit/comparison is done using residual deviance, leverage, and DIC.

## Limitations

  • The paper states that model choice can depend strongly on sparse data and prior distributions, and that deciding between fixed and random effects may be highly sensitive to these choices.
  • It notes that in network meta-analysis, consistency across evidence sources must be checked, because inconsistency can arise from trial-level effect modifiers.
  • Evident from the text: many assumptions are required for specific models, such as constant hazards for Poisson/log-link and cloglog models, and proportional competing risks for the multinomial competing-risks model; the paper presents these as model assumptions rather than validated facts.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1177/0272989x12458724

Cites

96 of 96 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Verification

Claims the paper makes

0 Valid · 0 Not valid · 11 Not checked · 19 Own results and interpretations

13 more claims

Create a free account to see all 30 claims and to verify the 13 references still open.

See all claims — free account
  • It may state two separate claims as one. 8
  • Probably not a substantial claim. 6

Create a free account to see these claims.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 96 references

Research works printed but not linked: 7

  1. Zelen M, 1971, Biometrika, 58, 129
  2. Welton NJ, 2005, Appl Stat, 54, 385
  3. 10.1002/(sici)1097-0258(19961230)15:24 · doi:10.1002/(sici)1097-0258(19961230)15:24
  4. National Institute for Health and Clinical Excellence, 2008, Guide to the Methods of Technology Appraisal
  5. Spiegelhalter D. Two brief topics on modelling with WinBUGS. IceBugs: a workshop about the development and use of the BUGS programme. Available from: http://www.math.helsinki.fi/openbugs/IceBUGS/Presentations/SpiegelhalterIceBUGS.pdf
  6. Rothman KJ, 2008, Modern Epidemiology
  7. Ades AE, 2005, Health Econ, 14, 373

Cited by

See all 1,207

Metadata

Authors
Dias, S., Sutton, A. J., Ades, A. E., & Welton, N. J.
Affiliations
University of Leicester (GB)
Corresponding author
Dias, Sofia
Venue
Medical Decision Making
Published
2012-10-26
Volume
33
Issue
5
Pages
607-617
ISSN
  • 0272-989X (ISSN-L)
  • 1552-681X
OpenAlex
W2150529573
Cited by
1,207
References
96
Citations by year
2026: 89 · 2025: 69 · 2024: 90 · 2023: 80 · 2022: 94 · 2021: 144 · 2020: 123 · 2019: 106 · 2018: 104 · 2017: 82 · 2016: 77 · 2015: 71 · 2014: 52 · 2013: 25 · 2012: 1
FWCI
55.08
Type
journal article
Language
en
Open access
Licence
  • cc-by-nc
  • journals.sagepub.com/page/policies/text-and-data-mining-license (tdm)
Locations
  • Medical Decision Making (publishedVersion, cc-by-nc)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by-nc)
  • PubMed Central (publishedVersion, cc-by-nc)
  • PubMed (publishedVersion)
  • RePEc: Research Papers in Economics (submittedVersion)
  • Explore Bristol Research (submittedVersion, cc-by-nc)
Topics
  • Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
  • Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Clinical Trials
  • Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
Keywords
generalized linear models, meta-analysis, randomized controlled trials, Bayesian meta-analysis, WinBUGS, link functions, network meta-analysis, indirect comparison, shared parameter models, deviance information criterion, Markov chain Monte Carlo, evidence synthesis
MeSH terms
Network Meta-Analysis as Topic, Decision Making, Models, Theoretical, Meta-Analysis as Topic, Likelihood Functions, Randomized Controlled Trials as Topic, Evidence-Based Medicine

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

A language model drew the claims from the paper on 2026-10-11, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Evidence Synthesis for Decision Making 2: A Generalized Linear Modeling Framework for Pairwise and Network Meta-analysis of Randomized Controlled Trials. https://app.cochat.ai/papers/10.1177/0272989x12458724
The paper
Dias, S., Sutton, A. J., Ades, A. E., & Welton, N. J. (2013). Evidence Synthesis for Decision Making 2: A Generalized Linear Modeling Framework for Pairwise and Network Meta-analysis of Randomized Controlled Trials. Medical Decision Making. https://doi.org/10.1177/0272989x12458724

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.