crmPack (version 2.2.1)

simulate,DesignCombo-method: Simulate outcomes from a two-drug combination CRM design

Description

Usage

# S4 method for DesignCombo
simulate(
  object,
  nsim = 1L,
  seed = NULL,
  truth,
  args = NULL,
  firstSeparate = FALSE,
  mcmcOptions = McmcOptions(),
  parallel = FALSE,
  nCores = min(parallel::detectCores(), 5),
  derive = list(),
  ...
)

Value

an object of class ComboSimulations

Arguments

object

the DesignCombo object we want to simulate data from

nsim

(count) the number of simulations (default: 1).

seed

see set_seed()

truth

(function) a function that takes as input a dose combination (named numeric vector of length 2) and returns the true DLT probability. Additional arguments can be supplied in args.

args

(data.frame) data frame with arguments for the truth function. The column names correspond to the argument names and rows are recycled across simulations.

firstSeparate

(flag) enroll the first patient separately from the rest of the cohort? If yes, the cohort is closed when a DLT occurs in this first patient.

mcmcOptions

(McmcOptions) MCMC options used for each trial evaluation.

parallel

(flag) should simulation runs be parallelized?

nCores

(count) number of cores used when parallel = TRUE.

derive

(list) named list of functions deriving extra statistics from posterior toxicity samples at the final recommended combination.

...

not used.

Examples

# nolint start

design_combo <- .DefaultDesignCombo()

true_tox_combo <- function(dose) {
  plogis(-6 + 0.08 * dose[1] + 0.06 * dose[2] + 0.001 * dose[1] * dose[2])
}

options <- McmcOptions(
  burnin = 50,
  step = 1,
  samples = 50,
  rng_kind = "Mersenne-Twister",
  rng_seed = 1
)

my_sims_combo <- simulate(
  design_combo,
  truth = true_tox_combo,
  nsim = 1,
  seed = 819,
  mcmcOptions = options,
  parallel = FALSE
)

# nolint end