Learn R Programming

nlme (version 3.1-144)

lmeControl: Specifying Control Values for lme Fit

Description

The values supplied in the lmeControl() call replace the defaults, and a list with all settings (i.e., values for all possible arguments) is returned. The returned list is used as the control argument to the lme function.

Usage

lmeControl(maxIter = 50, msMaxIter = 50, tolerance = 1e-6, niterEM = 25,
           msMaxEval = 200,
	   msTol = 1e-7, msVerbose = FALSE,
           returnObject = FALSE, gradHess = TRUE, apVar = TRUE,
	   .relStep = .Machine$double.eps^(1/3), minAbsParApVar = 0.05,
           opt = c("nlminb", "optim"),
	   optimMethod = "BFGS", natural = TRUE,
	   sigma = NULL,
           allow.n.lt.q = FALSE,
           …)

Arguments

maxIter

maximum number of iterations for the lme optimization algorithm. Default is 50.

msMaxIter

maximum number of iterations for the optimization step inside the lme optimization. Default is 50.

tolerance

tolerance for the convergence criterion in the lme algorithm. Default is 1e-6.

niterEM

number of iterations for the EM algorithm used to refine the initial estimates of the random effects variance-covariance coefficients. Default is 25.

msMaxEval

maximum number of evaluations of the objective function permitted for nlminb. Default is 200.

msTol

tolerance for the convergence criterion on the first iteration when optim is used. Default is 1e-7.

msVerbose

a logical value passed as the trace argument to nlminb or optim. Default is FALSE.

returnObject

a logical value indicating whether the fitted object should be returned with a warning (instead of an error via stop()) when the maximum number of iterations is reached without convergence of the algorithm. Default is FALSE.

gradHess

a logical value indicating whether numerical gradient vectors and Hessian matrices of the log-likelihood function should be used in the internal optimization. This option is only available when the correlation structure (corStruct) and the variance function structure (varFunc) have no "varying" parameters and the pdMat classes used in the random effects structure are pdSymm (general positive-definite), pdDiag (diagonal), pdIdent (multiple of the identity), or pdCompSymm (compound symmetry). Default is TRUE.

apVar

a logical value indicating whether the approximate covariance matrix of the variance-covariance parameters should be calculated. Default is TRUE.

.relStep

relative step for numerical derivatives calculations. Default is .Machine$double.eps^(1/3).

opt

the optimizer to be used, either "nlminb" (the default) or "optim".

optimMethod

character - the optimization method to be used with the optim optimizer. The default is "BFGS". An alternative is "L-BFGS-B".

minAbsParApVar

numeric value - minimum absolute parameter value in the approximate variance calculation. The default is 0.05.

natural

a logical value indicating whether the pdNatural parametrization should be used for general positive-definite matrices (pdSymm) in reStruct, when the approximate covariance matrix of the estimators is calculated. Default is TRUE.

sigma

optionally a positive number to fix the residual error at. If NULL, as by default, or 0, sigma is estimated.

allow.n.lt.q

logical indicating if it is ok to have less observations than random effects for each group. The default, FALSE signals an error; if NA, such a situation only gives a warning, as in nlme versions prior to 2019; if true, no message is given at all.

further named control arguments to be passed, depending on opt, to nlminb (those from abs.tol down) or optim (those except trace and maxit; reltol is used only from the second iteration).

Value

a list with components for each of the possible arguments.

See Also

lme, nlminb, optim

Examples

Run this code
# NOT RUN {
# decrease the maximum number iterations in the ms call and
# request that information on the evolution of the ms iterations be printed
str(lCtr <- lmeControl(msMaxIter = 20, msVerbose = TRUE))
## This should always work:
do.call(lmeControl, lCtr)
# }

Run the code above in your browser using DataLab