cats (version 1.0.2)

simulate_trial: Simulates the cohort trial.

Description

Simulates the cohort trial.

Usage

simulate_trial(
  n_fin,
  cohorts_start = 1,
  composite = "or",
  rr_comb1,
  rr_plac1,
  rr_comb2,
  rr_plac2,
  random_type = NULL,
  random = FALSE,
  correlation,
  prob_comb1_rr = NULL,
  prob_plac1_rr = NULL,
  prob_comb2_rr = NULL,
  prob_plac2_rr = NULL,
  stage_data = FALSE,
  cohort_random = NULL,
  cohorts_max = 4,
  sr_drugs_pos = 1,
  sr_pats = cohorts_max * (n_fin + 3 * cohorts_max),
  sr_first_pos = FALSE,
  cohort_offset = 0,
  sharing_type = "all",
  safety_prob = 0,
  cohorts_sim = Inf,
  missing_prob = 0,
  cohort_fixed = NULL,
  accrual_type = "fixed",
  accrual_param = 9,
  hist_lag = 48,
  analysis_times = c(0.5, 0.75, 1),
  time_trend = time_trend,
  ...
)

Arguments

n_fin

Sample size per cohort at final

cohorts_start

Number of cohorts to start the platform with

composite

Rule for deriving the composite endpoint. By default "or", otherwise "and"

rr_comb1

Response rates of treatment, histology endpoint 1

rr_plac1

Response rate of the SoC, histology endpoint 1

rr_comb2

Response rates of treatment, histology endpoint 2

rr_plac2

Response rate of the SoC, histology endpoint 2

random_type

How should the response rates be drawn randomly? Options are:

"absolute": Specify absolute response rates that will be drawn with a certain probability

"risk_difference": Specify absolute response rates for placebo which will be drawn randomly, plus specify vectors for absolute treatment effects of mono therapies over placebo and for combo over the mono therapies.

"risk_ratio": Specify absolute response rates for placebo which will be drawn randomly, plus specify vectors for relative treatment effects of mono therapies over placebo and for combo over the mono therapies.

"odds_ratios": Specify response rate for placebo, specify odds-ratios for mono therapies (via rr_back and rr_mono) and respective probabilities. On top, specify interaction for the combination therapy via rr_comb with prob_rr_comb.

Set: odds_combo = odds_plac * or_mono1 * or_mono2 * rr_comb. If rr_comb > 1 -> synergistic, if rr_comb = 1 -> additive. If rr_comb < 1 -> antagonistic. Default is "NULL".

random

Should the response rates of the arms be randomly drawn from rr_exp? Default is FALSE.

correlation

Correlation between histology endpoints

prob_comb1_rr

If random == TRUE, what are the probabilities with which the elements of rr_comb1 should be drawn?

prob_plac1_rr

If random == TRUE, what are the probabilities with which the elements of rr_plac1 should be drawn?

prob_comb2_rr

If random == TRUE, what are the probabilities with which the elements of rr_comb2 should be drawn?

prob_plac2_rr

If random == TRUE, what are the probabilities with which the elements of rr_plac2 should be drawn?

stage_data

Should individual stage data be passed along? Default is TRUE

cohort_random

If not NULL, indicates that new arms/cohorts should be randomly started. For every timestep, there is a cohort_random probability that a new cohort will be started.

cohorts_max

Maximum number of cohorts that are allowed to be added throughout the trial

sr_drugs_pos

Stopping rule for successful experimental arms; Default = 1

sr_pats

Stopping rule for total number of patients; Default = cohorts_max * n_fin + error term based on randomization

sr_first_pos

Stopping rule for first successful cohort; if TRUE, after first cohort was found to be successful, no further cohorts will be included but cohorts will finish evaluating, unless other stopping rules reached prior. Default is FALSE.

cohort_offset

Minimum number of time between adding new cohorts

sharing_type

Which backbone and placebo data should be used for arm comparisons; Default is "all". Another option is "concurrent" or "dynamic" or "cohort".

safety_prob

Probability for a random stopping after every patient

cohorts_sim

Maximum number of cohorts that can run simultaneously

missing_prob

Probability for a missing value at final (independent of treatment)

cohort_fixed

If not NULL, fixed timesteps after which a cohort will be included

accrual_type

Type of patient accrual; choices are "fixed", "poisson" or "exponential"

accrual_param

Parameter used for patient accrual

hist_lag

Time until histology outcome is observed

analysis_times

Vector of information fractions needed for first interim, second interim and final

time_trend

Additive term by which response rates increase at every time step

...

Further arguments to be passed to decision function, such as decision making criteria

Value

List containing: Responses and patients on experimental and control arm, total treatment successes and failures and final p-value

Examples

# NOT RUN {
random <- TRUE

rr_comb1 <- 0.10
prob_comb1_rr <- 1
rr_comb2 <- 0.45
prob_comb2_rr <- 1
rr_plac1 <- 0.10
prob_plac1_rr <- 1
rr_plac2 <- 0.20
prob_plac2_rr <- 1

correlation <- 0.8

cohorts_start <- 2
cohorts_max <- 5
safety_prob <- 0
sharing_type <- "concurrent"
sr_drugs_pos <- 5
sr_first_pos <- FALSE
n_fin <- 100
stage_data <- TRUE
cohort_random <- 0.01
cohort_offset <- 0
cohorts_sim <- Inf
random_type <- "absolute"
missing_prob <- 0.2
cohort_fixed <- 5
hist_lag <- 48
analysis_times <- c(0.5, 0.75, 1)
accrual_type <- "fixed"
accrual_param <- 9
time_trend <- 0.001
composite <- "or"

# Comparison IA1
Bayes_Sup11 <- matrix(nrow = 2, ncol = 2)
Bayes_Sup11[1,] <- c(0.00, 0.95)
Bayes_Sup11[2,] <- c(0.10, 0.80)
# Comparison IA2
Bayes_Sup12 <- matrix(nrow = 2, ncol = 2)
Bayes_Sup12[1,] <- c(0.00, 0.95)
Bayes_Sup12[2,] <- c(0.10, 0.80)
# Comparison IA3
Bayes_Sup13 <- matrix(nrow = 2, ncol = 2)
Bayes_Sup13[1,] <- c(0.00, 0.95)
Bayes_Sup13[2,] <- c(0.10, 0.80)

Bayes_Sup1 <- Bayes_Sup2 <- list(list(Bayes_Sup11), list(Bayes_Sup12), list(Bayes_Sup13))

# Comparison IA1
Bayes_Fut11 <- matrix(nrow = 1, ncol = 2)
Bayes_Fut11[1,] <- c(0.00, 0.20)
# Comparison IA2
Bayes_Fut12 <- matrix(nrow = 1, ncol = 2)
Bayes_Fut12[1,] <- c(0.00, 0.30)
# Comparison IA3
Bayes_Fut13 <- matrix(nrow = 1, ncol = 2)
Bayes_Fut13[1,] <- c(NA, NA)
# Endpoint 1+2
Bayes_Fut1 <- Bayes_Fut2 <- list(list(Bayes_Fut11), list(Bayes_Fut12), list(Bayes_Fut13))

simulate_trial(
 n_fin = n_fin, random_type = random_type, composite = composite,
 rr_comb1 = rr_comb1, rr_comb2 = rr_comb2, rr_plac1 = rr_plac1, rr_plac2 = rr_plac2,
 random = random, prob_comb1_rr = prob_comb1_rr, prob_comb2_rr = prob_comb2_rr,
 prob_plac1_rr = prob_plac1_rr, prob_plac2_rr = prob_plac2_rr, correlation = correlation,
 stage_data = stage_data, cohort_random = cohort_random, cohorts_max = cohorts_max,
 sr_drugs_pos = sr_drugs_pos, sharing_type = sharing_type, Bayes_Fut1 = Bayes_Fut1,
 safety_prob = safety_prob, Bayes_Sup1 = Bayes_Sup1, Bayes_Sup2 = Bayes_Sup2,
 cohort_offset = cohort_offset, sr_first_pos = sr_first_pos, Bayes_Fut2 = Bayes_Fut2,
 missing_prob = missing_prob, cohort_fixed = cohort_fixed, accrual_type = accrual_type,
 accrual_param = accrual_param, hist_lag = hist_lag, analysis_times = analysis_times,
 time_trend = time_trend, cohorts_start = cohorts_start, cohorts_sim = cohorts_sim
)

# }