Parametric G-Formula
Bootstrap Observed Data and Simulate Under All Interventions
Carry Forward
Coefficient method for objects of class "gformula"
General Error Catching
Fit Bounded Normal Model on Covariate
Fit GLM on Covariate
Fit Multinomial Model on Covariate
Fit Truncated Normal Model on Covariate
Fit Zero-Inflated Normal Model on Covariate
Get Covariate Plots
Get Risk and Survival Plots
Get Plotting Information
Estimation of Binary End-of-Follow-Up Outcome Under the Parametric G-F...
Estimation of Continuous End-of-Follow-Up Outcome Under the Parametric...
Estimation of Survival Outcome Under the Parametric G-Formula
Estimation of Survival Outcome, Continuous End-of-Follow-Up Outcome, o...
Format Simulated Dataset for Hazard Ratio Calculation
Execute Intervention
History functions
Generates Functions of History of Existing Covariates
Natural Course Intervention
Calculate Observed Covariate Means and Risk
Plot method for objects of class "gformula_binary_eof"
Plot method for objects of class "gformula_continuous_eof"
Plot method for objects of class "gformula_survival"
Fit Covariate Models
Fit Competing Event Model
Fit Outcome Model
Simulate Binary Values
Simulate Normal Values
Simulate Truncated Normal Values
Print and summary methods for "gformula" objects
Calculate RMSE for Covariate, Outcome, and Competing Risk Models
Simple Restriction
Simulate Counterfactual Outcomes Under Intervention
Static Intervention
Threshold Intervention
Variance-covariance method for objects of class "gformula"
Create Visit Sum Covariate
Implements the non-iterative conditional expectation (NICE) algorithm of the g-formula algorithm (Robins (1986) <doi:10.1016/0270-0255(86)90088-6>, Hernán and Robins (2024, ISBN:9781420076165)). 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. This package can be used for discrete or continuous time-varying treatments and for failure time outcomes or continuous/binary end of follow-up outcomes. The package can handle a random measurement/visit process and a priori knowledge of the data structure, as well as censoring (e.g., by loss to follow-up) and two options for handling competing events for failure time outcomes. Interventions can be flexibly specified, both as interventions on a single treatment or as joint interventions on multiple treatments. See McGrath et al. (2020) <doi:10.1016/j.patter.2020.100008> for a guide on how to use the package.
Useful links