Binary regression models with right censored outcomes
Response formula (e.g., Surv(time, event) ~ D + W).
Censoring formula (e.g., Surv(time, event == 0) ~ D + A + W)).
Optional treatment model (ml_model)
Optional prediction model (ml_model)
Optional data.frame. In this case the uncentered influence function evalued in 'newdata' is returned with nuisance parameters obtained from 'data'.
Time-point of interest, see Details.
"risk", "treatment", "rmst", "brier"
Number of folds in cross-fitting (M=1 is no cross-fitting).
Model call for the response model (e.g. "mets::phreg").
Additional arguments to the response model.
Similar to call.response.
Similar to args.response.
(optional) Data pre-processing function.
If FALSE an IPCW estimator is returned
Additional arguments to lower level data pre-processing functions.
The one-step estimator depends on the calculation of an integral
wrt. the martingale process corresponding to the counting process N(t) =
I(C>min(T,tau)). This can be decomposed into an integral wrt the counting
process, \(dN_c(t)\) and the compensator \(d\Lambda_c(t)\) where the
latter term can be computational intensive to calculate. Rather than
calculating this integral in all observed time points, we can make a
coarser evaluation which can be controlled by setting
N=0 the (computational intensive) standard evaluation is used.##'