rsurv: Simulation of survival data following a PCH model

In obouaziz/FastPseudo: Fast implementation of pseudo-observations for right-censored and interval censored data, for the survival function and the RMST

Description

Given a set of cuts and hazard values, generates a survival data sample from a piecewise-constant hazard (PCH) model.

Usage

rsurv(n, cuts = NULL, alpha)

Arguments

n	the sample size.
cuts	the sequence of cuts. Default to NULL which corresponds to the exponential model.
alpha	the value of the hazard function between each cut. Should be of length equal to length(cuts)+1.

Value

A time vector of size n drawn from a PCH model with hazard equal to alpha between cuts.

See Also

mleIC, pchcumhaz.

Examples

n=400
cuts=c(20,40,50,70)
alpha=c(0,0.05,0.1,0.2,0.4)/10
time=rsurv(n,cuts,alpha) #generate true data from the pch model
censoring=stats::runif(n,min=70,max=90)
time=pmin(time,censoring) #observed times
delta=time<censoring #gives 62% of observed data on average

obouaziz/FastPseudo documentation built on Dec. 22, 2021, 4:12 a.m.