The dark side of the force: multiplicity issues in network meta-analysis and how to address them.

Efthimiou, Orestis; White, Ian R (2020). The dark side of the force: multiplicity issues in network meta-analysis and how to address them. Research Synthesis Methods, 11(1), pp. 105-122. Wiley 10.1002/jrsm.1377

[img] Text
Efthimiou ResSynthMedods 2019_postprint.pdf - Accepted Version
Restricted to registered users only until 3 September 2020.
Available under License Publisher holds Copyright.

Download (1MB) | Request a copy

Standard models for network meta-analysis simultaneously estimate multiple relative treatment effects. In practice, after estimation, these multiple estimates usually pass through a formal or informal selection procedure, e.g. when researchers draw conclusions about the effects of the best performing treatment in the network. In this paper, we present theoretical arguments as well as results from simulations to illustrate how such practices might lead to exaggerated and overconfident statements regarding relative treatment effects. We discuss how the issue can be addressed via multi-level Bayesian modeling, where treatment effects are modeled exchangeably, and hence estimates are shrunk away from large values. We present a set of alternative models for network meta-analysis, and we show in simulations that in several scenarios, such models perform better than the usual network meta-analysis model.

Item Type:

Journal Article (Original Article)

Division/Institute:

04 Faculty of Medicine > Pre-clinic Human Medicine > Institute of Social and Preventive Medicine (ISPM)

UniBE Contributor:

Efthimiou, Orestis

Subjects:

600 Technology > 610 Medicine & health
300 Social sciences, sociology & anthropology > 360 Social problems & social services

ISSN:

1759-2879

Publisher:

Wiley

Funders:

[4] Swiss National Science Foundation

Language:

English

Submitter:

Beatrice Minder Wyssmann

Date Deposited:

09 Sep 2019 16:44

Last Modified:

19 Jan 2020 01:31

Publisher DOI:

10.1002/jrsm.1377

PubMed ID:

31476256

BORIS DOI:

10.7892/boris.133130

URI:

https://boris.unibe.ch/id/eprint/133130

Actions (login required)

Edit item Edit item
Provide Feedback