Evaluate the design candidate

The evaluation of the design candidate is independent of the optimization algorithm used.

evaluate_design_candidate(
  utility,
  design_candidate,
  prior_values,
  design_env,
  model,
  dudx,
  return_all,
  significance
)

Arguments

utility

A utility function

design_candidate

The current design candidate

prior_values

a list or vector of assumed priors

design_env

A design environment in which to evaluate the the function to derive the variance-covariance matrix.

model

A character string indicating the model to optimize the design for. Currently the only model programmed is the 'mnl' model and this is also set as the default.

dudx

A character string giving the name of the prior in the denominator. Must be specified when optimizing for 'c-error'

return_all

If `TRUE` return a K or K-1 vector with parameter specific error measures. Default is `FALSE`.

significance

A t-value corresponding to the desired level of significance. The default is significance at the 5 t-value of 1.96.

Value

A named vector with efficiency criteria of the current design candidate. If Bayesian prior_values are used, then it returns the average error.