rsControl: Options for the finite-difference covariance in setCov()
In nlmixr2est: Nonlinear Mixed Effects Models in Population PK/PD, Estimation Routines

rsControl

R Documentation

Options for the finite-difference covariance in setCov()

Description

Used by setCov(fit, "r,s"), "r" and "s". Each option left NULL keeps the value the fit was estimated with, except covFallback.

Usage

rsControl(
  hessEps = NULL,
  gillKcov = NULL,
  gillStepCov = NULL,
  gillFtolCov = NULL,
  covGillF = NULL,
  covSmall = NULL,
  rmatNorm = NULL,
  smatNorm = NULL,
  covFallback = NULL,
  covPrecursor,
  covShortcut = NULL
)

Arguments

`hessEps`	is a double value representing the epsilon for the Hessian calculation. This is used for the R matrix calculation.
`gillKcov`	Max steps to determine the optimal forward/central difference step size per parameter (Gill 1983) during the covariance step. '0' = no optimal step size determined.
`gillStepCov`	When looking for the optimal forward difference step size, this is This is the step size to increase the initial estimate by. So each iteration during the covariance step is equal to the new step size = (prior step size)*gillStepCov
`gillFtolCov`	The gillFtol is the gradient error tolerance that is acceptable before issuing a warning/error about the gradient estimates during the covariance step.
`covGillF`	Use the Gill calculated optimal Forward difference step size for the instead of the central difference step size during the central difference gradient calculation of the theta-only stage (see `covFull`).
`covSmall`	Small number used to compare covariance estimates (sandwich vs R/S matrix) before rejecting one as too small to be the final covariance estimate.
`rmatNorm`	A parameter to normalize gradient step size by the parameter value during the calculation of the R matrix of the theta-only stage (see `covFull`)
`smatNorm`	A parameter to normalize gradient step size by the parameter value during the calculation of the S matrix of the theta-only stage (see `covFull`)
`covFallback`	what the requested method may fall back to, as in `foceiControl(covFallback=)`. `NULL` (default) is none: `setCov()` installs the method asked for or stops with an error. With a list, a covariance from a method it lists for the request is installed, with a warning that names it.
`covPrecursor`	what the covariance may start from, as in `foceiControl(covPrecursor=)`. Left out, the fit's value is kept; `NULL` uses none.
`covShortcut`	as in `foceiControl(covShortcut=)`; `NULL` (default) keeps the fit's value.