baskexact (version 1.0.1)

check_mon_between: Check Between-Trial Monotonicity

Description

Checks whether the between-trial monotonicity condition holds.

Usage

check_mon_between(design, ...)
# S4 method for OneStageBasket
check_mon_between(
  design,
  n,
  lambda,
  weight_fun,
  weight_params = list(),
  details = TRUE,
  globalweight_fun = NULL,
  globalweight_params = list(),
  ...
)

Value

If details = FALSE then only a logical value is returned. If details = TRUE then if there are any cases where the between-trial monotonicity condition is violated, a list of theses cases and their results are returned.

Arguments

design

An object of class Basket created by setupOneStageBasket or setupTwoStageBasket.

...

Further arguments.

n

The sample size per basket.

lambda

The posterior probability threshold. See details for more information.

weight_fun

Which function should be used to calculate the pairwise weights.

weight_params

A list of tuning parameters specific to weight_fun.

details

Whether the cases where the monotonicity condition is violated should be returned, in case there are any.

globalweight_fun

Which function should be used to calculate the global weights.

globalweight_params

A list of tuning parameters specific to globalweight_fun.

Methods (by class)

• check_mon_between(OneStageBasket): Between-trial monotonicity condition for a single-stage design.

Details

check_mon_between checks whether the between-trial monotonicity condition holds. For a single-stage design with equal prior distributions and equal sample sizes for each basket this condition states that there are no cases where at least one null hypothesis is rejected when when there is a case with an equal or higher number of responses in each basket for which no null hypothesis is rejected.

If prune = TRUE then the baskets with an observed number of baskets smaller than the pooled critical value are not borrowed from. The pooled critical value is the smallest integer c for which all null hypotheses can be rejected if the number of responses is exactly c for all baskets.

The function is vectorized, such that vectors can be specified in weight_params and globalweight_params.

References

Baumann, L., Krisam, J., & Kieser, M. (2022). Monotonicity conditions for avoiding counterintuitive decisions in basket trials. Biometrical Journal, 64(5), 934-947.

Examples

design <- setupOneStageBasket(k = 4, shape1 = 1, shape2 = 1, p0 = 0.2)

# Without vectorization, with details
check_mon_between(design = design, n = 24, lambda = 0.99,
  weight_fun = weights_fujikawa, weight_params = list(epsilon = 3,
    tau = 0), details = TRUE)

# Vectorized
check_mon_between(design = design, n = 24, lambda = 0.99,
  weight_fun = weights_fujikawa,
  weight_params = list(epsilon = c(0.5, 1),  tau = c(0, 0.2, 0.3)),
  globalweight_fun = globalweights_fix,
  globalweight_params = list(w = c(0.5, 0.7)))