blackbox (version 1.1.46)

options: blackbox options settings

Description

Allow the user to examine a variety of “options” (most of which are not true user options) which affect operations of the blackbox package.

Usage

blackbox.options(...)
blackbox.getOption(x)

Value

For blackbox.getOption, the current value set for option x, or

NULL if the option is unset.

For blackbox.options(), a list of all set options. For

blackbox.options(name), a list of length one containing the set value, or NULL if it is unset. For uses setting one or more options, a list with the previous values of the options changed (returned invisibly).

Arguments

x

a character string holding an option name.

...

A named value or a list of named values. Most are not to be manipulated by users and are undocumented. Exceptions are:

ParameterNames

See Details

FONKgNames

See Details

fittedNames

See Details

gridStepsNbr

Number of steps of the grid of value for each parameter in profile plots.

graphicPars

Graphic parameters used for most plots.

coreNbr

Number of cores that R can use for parallel profile computations (see Details for implementation of these).

verbosity=0:

Controls display of information about generalized cross-validation. 0 suppresses (most) messages. 1 displays information about estimates and progress of the procedure. Higher values display more information from the optimizer and possibly additional information.

Details

blackbox.options() provides an interface for changing options, many of which are undocumented has they are intended to by used only in conjunction with the Migraine software, in which case the Migraine documentation should be consulted.

The package has been designed first to infer likelihood surfaces by smoothing estimated likelihood points in a model with some canonical parameters (ParameterNames). A transformed parameter space may be considered for smoothing, wherein some parameters are variable (fittedNames) and others may be constant. The transformed parameter space including constant parameters has names FONKgNames (FON for Fitted Or Not).

blackbox can perform in parallel manner the Migraine-specific computations of grids of profile log-likelihood values. See the Migraine documentation for user control of the requested number of cores; direct control through R code is possible by blackbox.options(coreNbr=.). If the doSNOW back-end is attached (by explicit request from the user), it will be used; otherwise, pbapply will be used. Both provide progress bars, but doSNOW may provide more efficient load-balancing.

Examples

  blackbox.getOption("verbosity")
  if (FALSE) {
  blackbox.options(verbosity=1)
  blackbox.options()
  }