bayes_adcock: Bayesian Assurance Computation in the Precision-Based Setting

In bayesassurance: Bayesian Assurance Computation

Bayesian Assurance Computation in the Precision-Based Setting

Description

Returns the Bayesian assurance of observing that the absolute difference between the true underlying population parameter and the sample estimate falls within a margin of error no greater than a fixed precision level, d.

Usage

bayes_adcock(
  n,
  d,
  mu_beta_a,
  mu_beta_d,
  n_a,
  n_d,
  sig_sq,
  alpha,
  mc_iter = 1000
)

Arguments

n	sample size (either vector or scalar).
d	fixed precision level
mu_beta_a	analysis stage mean
mu_beta_d	design stage mean
n_a	sample size at analysis stage. Also quantifies the amount of prior information we have for parameter μ.
n_d	sample size at design stage. Also quantifies the amount of prior information we have for where the data is being generated from.
sig_sq	known variance σ^2.
alpha	significance level
mc_iter	number of MC samples evaluated under the analysis objective

Value

approximate Bayesian assurance under precision-based conditions

Examples

n <- seq(20, 145, 5)
out <- bayes_adcock(n = n, d = 0.20, mu_beta_a = 0.64, mu_beta_d = 0.9,
                      n_a = 20, n_d = 10, sig_sq = 0.265,
                      alpha = 0.05, mc_iter = 1000)
head(out$assurance_table)
out$assurance_plot

bayesassurance documentation built on June 17, 2022, 5:05 p.m.