Example
This is a basic example which shows how to run simulations from a CRM with a 2-parameter logistic regression model, using a log normal prior distribution, and custom cohort size, stopping and maximum increments rules:
library(crmPack)
# Define the dose grid.
empty_data <- Data(doseGrid = c(1, 3, 5, 10, 15, 20, 25, 40, 50, 80, 100))
# Initialize the CRM model.
model <- LogisticLogNormal(
mean = c(-0.85, 1),
cov = matrix(c(1, -0.5, -0.5, 1), nrow = 2),
ref_dose = 56
)
# Choose the rule for selecting the next dose.
my_next_best <- NextBestNCRM(
target = c(0.2, 0.35),
overdose = c(0.35, 1),
max_overdose_prob = 0.25
)
# Choose the rule for the cohort size.
my_size_1 <- CohortSizeRange(
intervals = c(0, 30),
cohort_size = c(1, 3)
)
my_size_2 <- CohortSizeDLT(
intervals = c(0, 1),
cohort_size = c(1, 3)
)
my_size <- maxSize(my_size_1, my_size_2)
# Choose the rule for stopping.
my_stopping_1 <- StoppingMinCohorts(nCohorts = 3)
my_stopping_2 <- StoppingTargetProb(
target = c(0.2, 0.35),
prob = 0.5
)
my_stopping_3 <- StoppingMinPatients(nPatients = 20)
my_stopping <- (my_stopping_1 & my_stopping_2) | my_stopping_3
# Choose the rule for dose increments.
my_increments <- IncrementsRelative(
intervals = c(0, 20),
increments = c(1, 0.33)
)
# Initialize the design.
design <- Design(
model = model,
nextBest = my_next_best,
stopping = my_stopping,
increments = my_increments,
cohort_size = my_size,
data = empty_data,
startingDose = 3
)
# Define the true function.
my_truth <- function(dose) {
alpha0 <- 7
alpha1 <- 8
ref_dose <- 56
stand_log_dose <- log(dose / ref_dose)
plogis(alpha0 + alpha1 * stand_log_dose)
}
# Run the simulation on the desired design.
# We only generate 1 trial outcome here for illustration, for the actual study
# this should be increased of course.
options <- McmcOptions(
burnin = 100,
step = 1,
samples = 2000
)
time <- system.time(my_sims <- simulate(design,
args = NULL,
truth = my_truth,
nsim = 1,
seed = 819,
mcmcOptions = options,
parallel = FALSE
))[3]