The multinma package implements network meta-analysis, network meta-regression, and multilevel network meta-regression models which combine evidence from a network of studies and treatments using either aggregate data or individual patient data from each study (Phillippo et al. 2020; Phillippo 2019). Models are estimated in a Bayesian framework using Stan (Carpenter et al. 2017).

You can install the released version of multinma from CRAN with:

install.packages("multinma")

The development version can be installed from R-universe with:

install.packages("multinma", repos = c("https://dmphillippo.r-universe.dev", getOption("repos")))

or from source on GitHub with:

# install.packages("devtools")
devtools::install_github("dmphillippo/multinma")

Installing from source requires that the rstan package is installed and configured. See the installation guide here.

A good place to start is with the package vignettes which walk through example analyses, see vignette("vignette_overview") for an overview. The series of NICE Technical Support Documents on evidence synthesis gives a detailed introduction to network meta-analysis:

Dias, S. et al. (2011). “NICE DSU Technical Support Documents 1-7: Evidence Synthesis for Decision Making.” National Institute for Health and Care Excellence. Available from https://www.sheffield.ac.uk/nice-dsu/tsds.

Multilevel network meta-regression is set out in the following methods papers:

Phillippo, D. M. et al. (2020). “Multilevel Network Meta-Regression for population-adjusted treatment comparisons.” Journal of the Royal Statistical Society: Series A (Statistics in Society), 183(3):1189-1210. doi: 10.1111/rssa.12579.

Phillippo, D. M. et al. (2024). “Multilevel network meta-regression for general likelihoods: synthesis of individual and aggregate data with applications to survival analysis”. arXiv:2401.12640.

The multinma package can be cited as follows:

Phillippo, D. M. (2024). multinma: Bayesian Network Meta-Analysis of Individual and Aggregate Data. R package version 0.7.2.9000, doi: 10.5281/zenodo.3904454.

When fitting ML-NMR models, please cite the methods paper:

Phillippo, D. M. et al. (2020). “Multilevel Network Meta-Regression for population-adjusted treatment comparisons.” Journal of the Royal Statistical Society: Series A (Statistics in Society), 183(3):1189-1210. doi: 10.1111/rssa.12579.

For ML-NMR models with time-to-event outcomes, please cite:

Phillippo, D. M. et al. (2024). “Multilevel network meta-regression for general likelihoods: synthesis of individual and aggregate data with applications to survival analysis”. arXiv:2401.12640.