baskexact (version 1.0.1)

weights_cpp: Weights Based on the Calibrated Power Prior

Description

Weights Based on the Calibrated Power Prior

Usage

weights_cpp(design, ...)
# S4 method for OneStageBasket
weights_cpp(
  design,
  n,
  a = 1,
  b = 1,
  prune = FALSE,
  lambda,
  globalweight_fun = NULL,
  globalweight_params = list(),
  ...
)
# S4 method for TwoStageBasket
weights_cpp(design, n, n1, a = 1, b = 1, ...)

Value

A matrix including the weights of all possible pairwise outcomes.

Arguments

design

An object of class Basket created by setupOneStageBasket or setupTwoStageBasket.

...

Further arguments.

n

The sample size per basket.

a

first tuning parameter

b

second tuning parameter

prune

Whether baskets with a number of responses below the critical pooled value should be pruned before the final analysis. If this is TRUE then lambda is also required and if globalweight_fun is not NULL then globalweight_fun and globalweight_params are also used.

lambda

The posterior probability threshold. See details for more information.

globalweight_fun

Which function should be used to calculate the global weights.

globalweight_params

A list of tuning parameters specific to globalweight_fun.

n1

The sample size per basket for the interim analysis in case of a two-stage design.

Methods (by class)

• weights_cpp(OneStageBasket): Calibrated power prior weights for a single-stage basket design.

• weights_cpp(TwoStageBasket): Calibrated power prior weights for a two-stage basket design.

Details

weights_cpp calculates the weights based on an approach by Pan & Yuan (2017). The weight for two baskets i and j is found by at first calculating \(S_{KS;i,j}\) as the Kolmogorov-Smirnov statistic, which is equal to the difference in response rates for binary variables. \(S_{KS;i,j}\) is then transformed to \(S_{i,j} = n^{1/4}S_{KS;i,j}\). Then the weight is found as \(1 / (1 + exp(a + b * log(S_{i,j})))\), where a and b are tuning parameters.

The function is generally not called by the user but passed to another function such as toer and pow to specificy how the weights are calculated.

References

Baumann, L., Sauer, L., & Kieser, M. (2024). A basket trial design based on power priors. arXiv:2309.06988.

Pan, H., Yuan, Y., & Xia, J. (2017). A calibrated power prior approach to borrow information from historical data with application to biosimilar clinical trials. Journal of the Royal Statistical Society Series C: Applied Statistics, 66(5), 979-996.

Examples

design <- setupOneStageBasket(k = 3, p0 = 0.2)
toer(design, n = 15, lambda = 0.99, weight_fun = weights_cpp)