This class represents a Gaussian Commensurate Prior model: the commensurability link of Hobbs et al. (2011) without the power parameter, so that \(\theta_T | \theta_S, \tau \sim N(\theta_S, 1 / \tau)\) and the source likelihood enters undiscounted. Borrowing is then governed by the commensurability precision \(\tau\) alone.
Formally it is GaussianCommensuratePowerPrior at \(\gamma = 1\), which
is why it inherits from it: the data preparation, the three heterogeneity
prior families, the Stan program and the quadrature mixture are all the same
machinery, selected by borrows_power_parameter. Only the members that
mention \(\gamma\) are overridden here.
Super classes
Model -> MCMCModel -> GaussianCommensuratePowerPrior -> GaussianCommensuratePrior
Public fields
methodMethod name
borrows_power_parameterAlways
FALSEfor this modelstan_model_prefixPrefix of the compiled Stan model's name
summary_variablesVariables to summarise from the posterior draws
Methods
Inherited methods
Model$calibrate_for_design()Model$check_data()Model$create()Model$empirical_bayes_update()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_elir_ess()Model$prior_to_RBesT()Model$simulation_for_given_treatment_effect()Model$test_decision()MCMCModel$check_mcmc_config()MCMCModel$credible_interval()MCMCModel$draw_mcmc_prior()MCMCModel$inference()MCMCModel$posterior_cdf()MCMCModel$posterior_ess()MCMCModel$posterior_median()MCMCModel$posterior_pdf()MCMCModel$quadrature_posterior()MCMCModel$quadrature_prior()MCMCModel$sample_posterior()MCMCModel$stan_sampler()MCMCModel$summary_rows()MCMCModel$uses_quadrature()GaussianCommensuratePowerPrior$prepare_data()GaussianCommensuratePowerPrior$prior_cdf()GaussianCommensuratePowerPrior$prior_pdf()GaussianCommensuratePowerPrior$sample_prior()GaussianCommensuratePowerPrior$tau_posterior_moments()GaussianCommensuratePowerPrior$vectorised_replicate_inference()
GaussianCommensuratePrior$new()
Initialize the GaussianCommensuratePrior object
Usage
GaussianCommensuratePrior$new(prior, mcmc_config)GaussianCommensuratePrior$joint_prior_pdf()
Joint prior p.d.f. of the treatment effect and the commensurability parameter. Equation (8) in Hobbs et al (2011) with the power parameter fixed at one, so the Beta factor is absent and this takes one fewer argument than the power prior's version.