lpl (version 0.13)

rmst: The restricted mean survival time (RMST)

Description

Calculate the restricted mean survival time (RMST) for Surv object, Cox proportional model and other survival objects.

Usage

rmst(object, ...)
rmstFit(tau, h0 = NULL, H0 = function(x){x})
# S3 method for default
rmst(object, ...)
# S3 method for coxph
rmst(object, newdata = NULL, linear.predictors = NULL, tau=NULL, ...)
# S3 method for Surv
rmst(object, tau = NULL, ...)

Value

A value of the Brier score or integration of the Brier score is returned.

Arguments

object

for rmst.Surv and rmst.default, it is a survival object created by Surv(time, event). For others, it is a model object returned by coxph, lple.

h0

a hazard function to be used for restricted mean survival time calculation. If h0(t) is provided, then H0(t) will be ignored.

H0

a cumulative hazard function to be used for restricted mean survival time calculation. The default is H0(t) = t for t>0

linear.predictors

the linear predictor from the Cox PH model.

newdata

optional new data at which the RMST is calculated. If absent, RMST is for the dataframe used in the original model fit.

tau

the time point at which the restricted mean survival time is calculated.

...

additional arguments to be passed to the functions such as rmst.coxph, rmst.lple, rmst.Surv etc.

Author

Bingshu E. Chen

Details

The restricted mean survival time (RMST) is the mean of the truncated survival time at some finite value tau. The RMST is defined as,

RMST(tau) = E(min(T, tau)) = int_0 ^tau S(t)dt,

where S(t) = P(T>t) is the survival function of the random variable T.

rmstFit(tau, h0, H0) calculates the restricted mean survival time based on a hazard (or cumulative hazard) function. Only one function of either h0(t) or H0(t) is required. If h0(t) is provided, then H0(t) will be ignored.

See Also

coxph, Surv

Examples

  set.seed(29)
  n     = 25
  time  = rexp(n, 1)
  event = rbinom(n, 1, 0.75)
  x     = rnorm(n)
  y     = Surv(time, event)

  ### calculate the restricted mean survival time at tau = 0.5
  rms   = rmst(y, tau = 0.5)

  ### calculate the integrated brier score
  #fit   = coxph(y~x)
  #RMST  = rmst(fit, tau = 2)