survFit: Survival Curves for a Cox Proportional Hazards Model

Description

Computes the predicted survivor function for a Cox proportional hazards model.

Usage

# S3 method for mboost
survFit(object, newdata = NULL, ...)
# S3 method for survFit
plot(x, xlab = "Time", ylab = "Probability", ...)

Value

An object of class survFit containing the following components:

surv: the estimated survival probabilities at the time points given in time.
time: the time points at which the survivor functions are evaluated.
n.event: the number of events observed at each time point given in time.

Arguments

object: an object of class mboost which is assumed to have a CoxPH family component.
newdata: an optional data frame in which to look for variables with which to predict the survivor function.
x: an object of class survFit for plotting.
xlab: the label of the x axis.
ylab: the label of the y axis.
...: additional arguments passed to callies.

Details

If newdata = NULL, the survivor function of the Cox proportional hazards model is computed for the mean of the covariates used in the blackboost, gamboost, or glmboost call. The Breslow estimator is used for computing the baseline survivor function. If newdata is a data frame, the predict method of object, along with the Breslow estimator, is used for computing the predicted survivor function for each row in newdata.

Examples

Run this code


library("survival")
data("cancer", package = "survival")


fm <- Surv(futime,fustat) ~ age + resid.ds + rx + ecog.ps
fit <- glmboost(fm, data = ovarian, family = CoxPH(),
    control=boost_control(mstop = 500))

S1 <- survFit(fit)
S1
newdata <- ovarian[c(1,3,12),]
S2 <- survFit(fit, newdata = newdata)
S2

plot(S1)

Run the code above in your browser using DataLab

Data engineering and BI courses are free!