GaussianEmpiricalBayesPP class
Source:R/method_empirical_bayes_power_prior.R
GaussianEmpiricalBayesPP.RdThis is a parent class for variants of empirical Bayes PP methods for normally distributed summary measure of the treatment effect.
Super classes
Model -> GaussianConjugate -> GaussianStaticBorrowing -> GaussianEmpiricalBayesPP
Public fields
power_parameterThe power parameter.
summary_measure_likelihoodThe summary measure distribution.
null_spaceNull hypothesis space.
empirical_bayesBoolean indicating if empirical Bayes is used.
Methods
Inherited methods
Model$calibrate_for_design()Model$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_ess()Model$posterior_quantile()Model$print_model_summary()Model$prior_elir_ess()Model$simulation_for_given_treatment_effect()Model$test_decision()GaussianConjugate$credible_interval()GaussianConjugate$posterior_cdf()GaussianConjugate$posterior_mean()GaussianConjugate$posterior_median()GaussianConjugate$posterior_moments()GaussianConjugate$posterior_pdf()GaussianConjugate$posterior_to_RBesT()GaussianConjugate$posterior_variance()GaussianConjugate$prior_cdf()GaussianConjugate$prior_to_RBesT()GaussianConjugate$sample_posterior()GaussianConjugate$sample_prior()GaussianConjugate$vectorised_replicate_inference()GaussianStaticBorrowing$summary_rows()
GaussianEmpiricalBayesPP$new()
Initialize the GaussianEmpiricalBayesPP object.
Usage
GaussianEmpiricalBayesPP$new(prior, null_space, theta_0)GaussianEmpiricalBayesPP$vectorised_power_parameter()
Estimate the power parameter for every replicate at once
Subclasses whose estimator is closed form override this. Returning NULL
means "no fast path", which keeps subclasses with an iterative estimator
(PDCCPP calibrates by search) on the replicate loop.
GaussianEmpiricalBayesPP$vectorised_prior_variance()
Prior variance for each replicate
Mirrors empirical_bayes_update(): the power prior is equivalent to a
Gaussian prior with variance source standard error^2 / power parameter,
and a power parameter of zero means a vague prior.
GaussianEmpiricalBayesPP$vectorised_posterior_parameters()
Posterior parameters reported by the vectorised path
GaussianEmpiricalBayesPP$prior_pdf()
Calculate the prior probability density function (PDF) for a given target treatment effect.
GaussianEmpiricalBayesPP$plot_power_parameter_vs_drift()
Plot the power parameter as a function of drift in treatment effect
Usage
GaussianEmpiricalBayesPP$plot_power_parameter_vs_drift(
source_treatment_effect_estimate,
target_data,
min_drift,
max_drift,
resolution
)