The causalCmprsk
package is designed for estimation of
average treatment effects (ATE) of point interventions/treatments on
time-to-event outcomes with K competing events (K can be 1). The method
assumes that there is no unmeasured confounding and uses propensity
scores weighting for emulation of baseline randomization.
The causalCmprsk
package provides two main functions:
fit.cox
which assumes the Cox proportional hazards
regression for potential outcomes, and fit.nonpar
that does
not make any modeling assumptions for potential outcomes.
The causalCmprsk
package can be installed by
devtools::install_github("Bella2001/causalCmprsk")
The examples of how to use causalCmprsk
package on real
data can be found here.