Quantiles2LogisticNormal: Convert prior quantiles (lower, median, upper) to logistic (log) normal model

Description

This function uses generalised simulated annealing to optimise a LogisticNormal model to be as close as possible to the given prior quantiles.

Usage

Quantiles2LogisticNormal(
  dosegrid,
  refDose,
  lower,
  median,
  upper,
  level = 0.95,
  logNormal = FALSE,
  parstart = NULL,
  parlower = c(-10, -10, 0, 0, -0.95),
  parupper = c(10, 10, 10, 10, 0.95),
  seed = 12345,
  verbose = TRUE,
  control = list(threshold.stop = 0.01, maxit = 50000, temperature = 50000, max.time =
    600)
)

Value

a list with the best approximating model

(LogisticNormal or LogisticLogNormal), the resulting quantiles, the required quantiles and the distance to the required quantiles, as well as the final parameters (which could be used for running the algorithm a second time)

Arguments

dosegrid: the dose grid
refDose: the reference dose
lower: the lower quantiles
median: the medians
upper: the upper quantiles
level: the credible level of the (lower, upper) intervals (default: 0.95)
logNormal: use the log-normal prior? (not default) otherwise, the normal prior for the logistic regression coefficients is used
parstart: starting values for the parameters. By default, these are determined from the medians supplied.
parlower: lower bounds on the parameters (intercept alpha and the slope beta, the corresponding standard deviations and the correlation.)
parupper: upper bounds on the parameters
seed: seed for random number generation
verbose: be verbose? (default)
control: additional options for the optimisation routine, see GenSA for more details