gnlsControl function

Control Values for gnls Fit

The values supplied in the function call replace the defaults and a list with all possible arguments is returned. The returned list is used as the control argument to the gnls function.

gnlsControl(maxIter = 50, nlsMaxIter = 7, msMaxIter = 50, minScale = 0.001,
            tolerance = 1e-6, nlsTol = 0.001, msTol = 1e-7,
            returnObject = FALSE, msVerbose = FALSE,
            apVar = TRUE, .relStep =,
            opt = c("nlminb", "optim"), optimMethod = "BFGS",
            minAbsParApVar = 0.05, sigma = NULL)

Arguments

• maxIter: maximum number of iterations for the gnls

  optimization algorithm. Default is 50.

• nlsMaxIter: maximum number of iterations for the nls optimization step inside the gnls

  optimization. Default is 7.

• msMaxIter: maximum number of iterations for the optimization step inside the gnls

  optimization. Default is 50.

• minScale: minimum factor by which to shrink the default step size in an attempt to decrease the sum of squares in the nls step. Default 0.001.

• tolerance: tolerance for the convergence criterion in the gnls algorithm. Default is 1e-6.

• nlsTol: tolerance for the convergence criterion in nls

  step. Default is 1e-3.

• msTol: tolerance for the convergence criterion of the first outer iteration when optim is used. Default is 1e-7.

• 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.

• msVerbose: a logical value passed as the trace argument to the optimizer chosen by opt; see documentation on that. Default is FALSE.

• 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) (about 6e-6).

• opt: the optimizer to be used, either "nlminb" (the current default) or "optim" (the previous default).

• 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.

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

Returns

a list with components for each of the possible arguments.

Author(s)

José Pinheiro and Douglas Bates bates@stat.wisc.edu ; the sigma option: Siem Heisterkamp and Bert van Willigen.

See Also

gnls

Examples

# decrease the maximum number of iterations and request tracing
gnlsControl(msMaxIter = 20, msVerbose = TRUE)