simStudy: A function to simulate Survival data

In iain-t-bennett/SwitchPack: Tools To Facilitate Analysis Of Trials Affected By Crossover

Description

This function simulates survival data with correlated time to progression and overall survival times.

Usage

simStudy(simid = 1, seed = 1234, rho = 0, p.switch = 0.25,
  prop.pd.int = 0, beta_1a = log(0.7), beta_1b = log(0.7),
  beta_2a = log(0.7), beta_2b = log(0.7), beta_pd = log(0.4),
  arm.n = 250, enroll.start = 0, enroll.end = 2, admin.censor = 3,
  os.gamma = 1.2, os.lambda = 0.3, ttp.gamma = 1.5, ttp.lambda = 2,
  include.metadata = FALSE)

Arguments

simid	Identifer added to simulated dataframe. Defaults to 1.
seed	Seed used for random number generator. Defaults to 1234.
rho	correlation coefficient between TTP and OS. Defaults to 0.
p.switch	proportion of patients who switch. Defaults to 0.25.
prop.pd.int	proportion of patients with PFS before switch allowed. Defaults to 0.
beta_1a	treatment effect (as log(Hazard Ratio)). Defaults to log(0.7).
beta_1b	treatment effect (as log(Hazard Ratio)). Defaults to log(0.7).
beta_2a	treatment effect (as log(Hazard Ratio)). Defaults to log(0.7).
beta_2b	treatment effect (as log(Hazard Ratio)). Defaults to log(0.7).
beta_pd	treatment effect on prog (as log(HR)). Defaults to log(0.4).
arm.n	patients per arm. Defaults to 250.
enroll.start	start of enrollment. Defaults to 0.
enroll.end	end of enrollment. Defaults to 2.
admin.censor	end of trial. Defaults to 3.
os.gamma	weibull shape - for OS. Defaults to 1.2.
os.lambda	weibull scale - for OS. Defaults to 0.3.
ttp.gamma	weibull shape - for TTP. Defaults to 1.5.
ttp.lambda	weibull scale - for TTP. Defaults to 2.
include.metadata	Should returned dataframe include simulation parameters. Defaults to False.

Examples

require(survival)
require(dplyr)

tst.df <- simStudy()
survfit(Surv(pfs.t, event = pfs.e) ~ x.trt, data = tst.df) %>%
  plot()

survfit(Surv(os.t, event = os.e) ~ x.trt, data = tst.df) %>%
  plot()

iain-t-bennett/SwitchPack documentation built on May 16, 2019, 11:07 a.m.