Parametric G-Formula

Implements the parametric g-formula algorithm of Robins (1986) . The g-formula can be used to estimate the causal effects of hypothetical time-varying treatment interventions on the mean or risk of an outcome from longitudinal data with time-varying confounding. This package allows: 1) binary or continuous/multi-level time-varying treatments; 2) different types of outcomes (survival or continuous/binary end of follow-up); 3) data with competing events or truncation by death and loss to follow-up and other types of censoring events; 4) different options for handling competing events in the case of survival outcomes; 5) a random measurement/visit process; 6) joint interventions on multiple treatments; and 7) general incorporation of a priori knowledge of the data structure.


Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.


0.3.1 by Sean McGrath, 8 months ago,

Report a bug at

Browse source code at

Authors: Victoria Lin [aut] (V. Lin and S. McGrath made equal contributions) , Sean McGrath [aut, cre] , V. Lin and S. McGrath made equal contributions) , Zilu Zhang [aut] , Roger W. Logan [aut] , Lucia C. Petito [aut] , Jessica G. Young [aut] , M.A. Hernán and J.G. Young made equal contributions) , Miguel A. Hernán [aut] (M.A. Hernán and J.G. Young made equal contributions) , 2019 The President and Fellows of Harvard College [cph]

Documentation:   PDF Manual  

GPL-3 license

Imports data.table, ggplot2, ggpubr, grDevices, nnet, parallel, progress, stats, stringr, survival, truncnorm, truncreg, utils

Suggests Hmisc

See at CRAN