Skip to content

The pygformula implements the parametric g-formula in Python. The parametric g-formula (Robins, 1986) uses longitudinal data with time-varying treatments and confounders to estimate the risk or mean of an outcome under hypothetical treatment strategies specified by the user.

License

Notifications You must be signed in to change notification settings

CausalInference/pygformula

Repository files navigation

pygformula: a python implementation of the parametric g-formula

PyPI version Documentation Status Downloads

Authors: Jing Li, Sophia Rein, Sean McGrath, Roger Logan, Ryan O’Dea, Miguel Hernán

Overview

The pygformula package implements the non-iterative conditional expectation (NICE) estimator of the g-formula algorithm (Robins, 1986). The g-formula can estimate an outcome’s counterfactual mean or risk under hypothetical treatment strategies (interventions) when there is sufficient information on time-varying treatments and confounders.

Features

  • Treatments: discrete or continuous time-varying treatments.
  • Outcomes: failure time outcomes or continuous/binary end of follow-up outcomes.
  • Interventions: interventions on a single treatment or joint interventions on multiple treatments.
  • Random measurement/visit process.
  • Incorporation of a priori knowledge of the data structure.
  • Censoring events.
  • Competing events.

Requirements

The package requires python 3.8+ and these necessary dependencies:

  • cmprsk
  • joblib
  • lifelines
  • matplotlib
  • numpy
  • pandas
  • prettytable
  • pytruncreg
  • scipy
  • seaborn
  • statsmodels
  • tqdm

Documentation

The online documentation is available at pygformula documentation.

Issues

If you have any issues, please open an issue on github, we will regularly check the questions. For any additional questions or comments, please email jing_li@hsph.harvard.edu.

About

The pygformula implements the parametric g-formula in Python. The parametric g-formula (Robins, 1986) uses longitudinal data with time-varying treatments and confounders to estimate the risk or mean of an outcome under hypothetical treatment strategies specified by the user.

Topics

Resources

License

Stars

Watchers

Forks

Languages