sim_fixed_n: Simulation of fixed sample size design for time-to-event...

In keaven/simtrial: Clinical Trial Simulation

Simulation of fixed sample size design for time-to-event endpoint

Description

sim_fixed_n() provide simulations of a single endpoint two-arm trial where the enrollment, hazard ratio, and failure and dropout rates change over time.

Usage

sim_fixed_n(
  nsim = 1000,
  sampleSize = 500,
  target_event = 350,
  strata = tibble(Stratum = "All", p = 1),
  enroll_rate = tibble(duration = c(2, 2, 10), rate = c(3, 6, 9)),
  fail_rate = tibble(Stratum = "All", duration = c(3, 100), fail_rate = log(2)/c(9, 18),
    hr = c(0.9, 0.6), dropoutRate = rep(0.001, 2)),
  totalDuration = 30,
  block = rep(c("Experimental", "Control"), 2),
  timingType = 1:5,
  rg = tibble(rho = 0, gamma = 0),
  seed = NULL
)

Arguments

nsim	Number of simulations to perform.
sampleSize	Total sample size per simulation.
target_event	Targeted event count for analysis.
strata	A tibble with strata specified in Stratum, probability (incidence) of each stratum in p.
enroll_rate	Piecewise constant enrollment rates by time period. Note that these are overall population enrollment rates and the strata argument controls the random distribution between strata.
fail_rate	Piecewise constant control group failure rates, hazard ratio for experimental vs control, and dropout rates by stratum and time period.
totalDuration	Total follow-up from start of enrollment to data cutoff.
block	As in simtrial::sim_pw_surv(). Vector of treatments to be included in each block.
timingType	A numeric vector determining data cutoffs used; see details. Default is to include all available cutoff methods.
rg	As in simtrial::tenFHCorr(). A tibble with variables rho and gamma, both greater than equal to zero, to specify one Fleming-Harrington weighted logrank test per row.
seed	Optional. Initial seed for simulations

Details

timingType has up to 5 elements indicating different options for data cutoff. 1 uses the planned study duration, 2 the time the targeted event count is achieved, 3 the planned minimum follow-up after enrollment is complete, 4 the maximum of planned study duration and targeted event count cuts (1 and 2), 5 the maximum of targeted event count and minimum follow-up cuts (2 and 3).

Value

A tibble including columns Events (event count), lnhr (log-hazard ratio), Z (normal test statistic; < 0 favors experimental) cut (text describing cutoff used), Duration (duration of trial at cutoff for analysis) and sim (sequential simulation id). One row per simulated dataset per cutoff specified in timingType, per test statistic specified. If multiple Fleming-Harrington tests are specified in rg, then columns rho,gamma are also included.

Examples

library(tidyr)
library(dplyr)
library(doParallel)
library(tibble)

# example 1
# Show output structure
sim_fixed_n(nsim = 3)

# example 2
# Example with 2 tests: logrank and FH(0,1)
sim_fixed_n(nsim = 1,rg = tibble(rho = 0, gamma = c(0, 1)))

# example 3
# Power by test
# Only use cuts for events, events + min follow-up
xx <- sim_fixed_n(nsim = 100,
             timingType = c(2, 5),
             rg = tibble(rho = 0, gamma = c(0, 1)))
# Get power approximation for FH, data cutoff combination
xx %>%
  group_by(cut, rho, gamma) %>%
  summarise(mean(Z <= qnorm(.025)))

# MaxCombo power estimate for cutoff at max of targeted events, minimum follow-up
p <- xx %>%
  filter(cut != "Targeted events") %>%
  group_by(Sim) %>%
  group_map(pvalue_maxcombo) %>%
  unlist()

mean(p < .025)

# MaxCombo estimate for targeted events cutoff
p <- xx %>%
  filter(cut == "Targeted events") %>%
  group_by(Sim) %>%
  group_map(pvalue_maxcombo) %>%
  unlist()

mean(p < .025)

# example 3
# Use two cores
registerDoParallel(2)
sim_fixed_n(nsim = 10, seed = 2022)
stopImplicitCluster()
registerDoSEQ()

keaven/simtrial documentation built on April 17, 2023, 4:03 a.m.