mrgoptim: Fit a model to data using maximum likelihood objective...

In mhismail/mrgsolvetk: Simulation Tool Kit for mrgsolve

Fit a model to data using maximum likelihood objective function with newuoa or optim

Description

Fit a model to data using maximum likelihood objective function with newuoa or optim

Usage

mrgoptim(
  mod,
  output = "ipred",
  var = "var",
  prms,
  v_prms,
  cov = TRUE,
  restarts = 0,
  method = c("newuoa", "bobyqa", "Nelder-Mead", "BFGS", "CG", "L-BFGS-B", "SANN",
    "Brent"),
  upper = Inf,
  lower = -Inf,
  options = switch(method, newuoa = list(iprint = 5), bobyqa = list(iprint = 5),
    list(trace = 2)),
  ...
)

Arguments

mod	a model object
output	a character string containing name of prediction output column
var	a character string containing name of variance output column of predictions
prms	a character vector of parameters to fit
v_prms	a character vector of variance parameters to fit
cov	logical, perform covariance step
restarts	number of times to restart fit with final estimates of previous optimization
method	method to be used: "newuoa", "bobyqa", "Nelder-Mead", "BFGS", "CG", "L-BFGS-B", "SANN", "Brent"
upper	A numeric vector of upper bounds on the parameters. If the length is 1 the single upper bound is applied to all parameters. (only used for methods bobyqa, L-BFGS-B, Brent)
lower	A numeric vector of lower bounds on the parameters. If the length is 1 the single lower bound is applied to all parameters. (only used for methods bobyqa, L-BFGS-B, Brent)
options	options passed to optim function, see ?optim, ?newuoa, or ?bobyqa for more information
...	further arguments passed to mrgsim function

mhismail/mrgsolvetk documentation built on May 7, 2023, 1:52 p.m.