Parametric Iterative Conditional Expectation G-Formula
Dynamic
Strategy with Grace Period
Iterative Conditional Expectation Estimator
Natural Course
Plot method for ICE estimator objects
Indicator for the pooling over treatment history ICE estimator
Static
Indicator for the stratifying on treatment history ICE estimator
Summary method for ICE Estimator Objects
Threshold
Indicator for the doubly robust ICE estimator
Implements iterative conditional expectation (ICE) estimators of the plug-in g-formula (Wen, Young, Robins, and Hernán (2020) <doi:10.1111/biom.13321>). Both singly robust and doubly robust ICE estimators based on parametric models are available. The package can be used to estimate survival curves under sustained treatment strategies (interventions) using longitudinal data with time-varying treatments, time-varying confounders, censoring, and competing events. The interventions can be static or dynamic, and deterministic or stochastic (including threshold interventions). Both prespecified and user-defined interventions are available.