simulateDiscreteSaemix: Perform simulations under the model for an saemixObject...

In saemix: Stochastic Approximation Expectation Maximization (SAEM) Algorithm

Perform simulations under the model for an saemixObject object defined by its log-likelihood

Description

This function is used to simulate from discrete response models.

Usage

simulateDiscreteSaemix(
  object,
  nsim,
  seed,
  predictions = TRUE,
  uncertainty = FALSE,
  verbose = FALSE
)

Arguments

object	an saemixObject object returned by the saemix function. The model must contain a slot simulate.function, containing a function with the same structure as the model functions (arguments (psi, id, xidep)) which returns simulated responses when given a set of individual parameters (psi) and the corresponding predictors (xidep)
nsim	Number of simulations to perform. Defaults to the nb.simpred element in options
seed	if non-null, seed used to initiate the random number generator (defaults to NULL)
predictions	Whether the simulated parameters should be used to compute predictions. Defaults to TRUE. If FALSE, only individual parameters are simulated.
uncertainty	Uses uncertainty (currently not implemented). Defaults to FALSE
verbose	if TRUE, prints messages (defaults to FALSE)

Details

To call this function, the user needs to define a simulate.function matching the model function in the object. The function will then be used to simulate data under the empirical design, using the model and estimated parameters from a fit.

This function calls simulate.SaemixObject with the prediction=FALSE option to simulate individual parameters, then the simulate.function to obtain corresponding predictions.

Author(s)

Emmanuelle Comets [e-mail]

See Also

SaemixObject,saemix, simulate.SaemixObject

saemix documentation built on May 29, 2024, 10:43 a.m.