G-Formula for Causal Inference via Multiple Imputation

Implements the G-Formula method for causal inference with time-varying treatments and confounders using Bayesian multiple imputation methods, as described by Bartlett et al (2025) . It creates multiple synthetic imputed datasets under treatment regimes of interest using the 'mice' package. These can then be analysed using rules developed for analysing multiple synthetic datasets.

gFormulaMI

gFormulaMI is an R package that implements the G-formula method for causal inference with time-varying treatments and confounders using multiple imputation methods. For more information, including examples, see the 'Get Started' page.

Installation

You can install the development version of gFormulaMI from GitHub with:

# install.packages("devtools")
devtools::install_github("jwb133/gFormulaMI")