performBayesianMCPMod: performBayesianMCPMod

In BayesianMCPMod: Simulate, Evaluate, and Analyze Dose Finding Trials with Bayesian MCPMod

performBayesianMCPMod

Description

Performs Bayesian MCP Test step and modeling in a combined fashion. See performBayesianMCP() function for MCP Test step and getModelFits() for the modeling step

Usage

performBayesianMCPMod(
  posterior_list,
  contr,
  crit_prob_adj,
  simple = FALSE,
  avg_fit = TRUE,
  delta = NULL,
  evidence_level = NULL,
  med_selection = c("avgFit", "bestFit"),
  n_samples = 1000
)

Arguments

posterior_list	An object of class 'postList' as created by getPosterior() containing information about the (mixture) posterior distribution per dose group
contr	An object of class 'optContr' as created by the getContr() function. It contains the contrast matrix to be used for the testing step.
crit_prob_adj	A getCritProb object, specifying the critical value to be used for the testing (on the probability scale).
simple	Boolean variable, defining whether simplified fit will be applied. Passed to the getModelFits() function. Default FALSE.
avg_fit	Boolean variable, defining whether an average fit (based on generalized AIC weights) should be performed in addition to the individual models. Default TRUE.
delta	A numeric value for the threshold Delta for the MED assessment. If NULL, no MED assessment is performed. Default NULL.
evidence_level	A numeric value between 0 and 1 for the evidence level gamma for the MED assessment. Only required for Bayesian MED assessment, see ?getMED for details. Default NULL.
med_selection	A string, either "avgFit" or "bestFit" based on the lowest gAIC, for the method of MED selection. Default "avgFit".
n_samples	A numerical for the number of bootstrapped samples in case the Bayesian MED assessment is performed. Default 1e3.

Value

Bayesian MCP test result as well as modeling result.

Examples

mods <- DoseFinding::Mods(linear      = NULL,
                          emax        = c(0.5, 1.2),
                          exponential = 2,
                          doses       = c(0, 0.5, 2,4, 8))
dose_levels  <- c(0, 0.5, 2, 4, 8)
sd_posterior <- c(2.8, 3, 2.5, 3.5, 4)
contr_mat <- getContr(
  mods         = mods,
  dose_levels  = dose_levels,
  sd_posterior = sd_posterior)
critVal <- getCritProb(
  mods           = mods,
  dose_weights   = c(50, 50, 50, 50, 50), #reflecting the planned sample size
  dose_levels    = dose_levels,
  alpha_crit_val = 0.6) # unreasonable alpha for this example, rather choose 0.05
prior_list <- list(Ctrl = RBesT::mixnorm(comp1 = c(w = 1, m = 0, s = 5), sigma = 2),
                   DG_1 = RBesT::mixnorm(comp1 = c(w = 1, m = 1, s = 12), sigma = 2),
                   DG_2 = RBesT::mixnorm(comp1 = c(w = 1, m = 1.2, s = 11), sigma = 2) ,
                   DG_3 = RBesT::mixnorm(comp1 = c(w = 1, m = 1.3, s = 11), sigma = 2) ,
                   DG_4 = RBesT::mixnorm(comp1 = c(w = 1, m = 2, s = 13), sigma = 2))
mu <- c(0, 1, 1.5, 2, 2.5)
S_hat <- c(5, 4, 6, 7, 8)
posterior_list <- getPosterior(
  prior_list = prior_list,
  mu_hat     = mu,
  S_hat      = S_hat,
  calc_ess   = TRUE)
                      
performBayesianMCPMod(posterior_list = posterior_list,
                      contr          = contr_mat,
                      crit_prob_adj  = critVal,
                      simple         = FALSE,
                      delta          = 1)

BayesianMCPMod documentation built on April 4, 2025, 5:24 a.m.