The calibrated power prior of GaussianPDCCPP for a binary endpoint:
the power parameter is given by the same rule, applied to the estimated
risk differences and their standard errors, the target data are analysed
with the binomial conditional power prior of BinomialCPP at that power
parameter, and the calibration parameter is calibrated on the exact type I
error of this binomial analysis rather than on the closed form of a normal
one; see the comment at the top of R/binomial_pdccpp.R.
The calibration needs the design, which Model$calibrate_for_design()
records, and the critical value the analysis decides at, which is only
known once a replicate is analysed, so it runs at the first replicate.
Super classes
Model -> MCMCModel -> BinomialCPP -> BinomialPDCCPP
Public fields
methodMethod name.
empirical_bayesThe prior depends on the target data.
empirical_bayes_from_sampleThe prior is a function of the replicate's sample alone.
fixed_power_parameterThe power parameter changes between replicates.
null_spaceSide of the null hypothesis space.
theta_0Boundary of the null hypothesis space.
designThe target data of the design calibrated against.
calibrationThe calibration parameter and its exact type I error.
Methods
Inherited methods
Model$check_data()Model$create()Model$estimate_bayesian_operating_characteristics()Model$estimate_frequentist_operating_characteristics()Model$hypothesis_space_transformation()Model$inference_cache_scope()Model$plot_pdfs()Model$plot_posterior_pdf()Model$plot_prior_pdf()Model$posterior_beta_mixture()Model$posterior_mean()Model$posterior_moments()Model$posterior_quantile()Model$posterior_to_RBesT()Model$print_model_summary()Model$prior_to_RBesT()Model$simulation_for_given_treatment_effect()Model$test_decision()Model$vectorised_replicate_inference()MCMCModel$check_mcmc_config()MCMCModel$compute_posterior_parameters()MCMCModel$credible_interval()MCMCModel$inference()MCMCModel$posterior_cdf()MCMCModel$posterior_ess()MCMCModel$posterior_median()MCMCModel$posterior_pdf()MCMCModel$prior_cdf()MCMCModel$prior_pdf()MCMCModel$sample_posterior()MCMCModel$sample_prior()MCMCModel$stan_sampler()MCMCModel$uses_quadrature()BinomialCPP$draw_mcmc_prior()BinomialCPP$prepare_data()BinomialCPP$prior_given_control_rate()BinomialCPP$quadrature_posterior()BinomialCPP$quadrature_prior()BinomialCPP$summary_rows()
BinomialPDCCPP$new()
Initialize a BinomialPDCCPP model.
Usage
BinomialPDCCPP$new(prior, theta_0, null_space, mcmc_config)BinomialPDCCPP$ensure_calibrated()
Calibrate, if not done yet for the current design and critical value.
BinomialPDCCPP$prior_elir_ess()
ELIR effective sample size of the current prior,
interpolated over the power parameter; see
binomial_power_prior_unit_elir().