VarReg.control {VarReg}

Auxillary for controlling VarReg fitting

Description

Use VarReg.control to determine parameters for the fitting of semiVarReg. Typically only used internally within functions.

Usage

VarReg.control(bound.tol = 1e-05, epsilon = 1e-06, maxit = 1000)

Arguments

bound.tol

Positive tolerance for specifying the interior of the parameter space. This allows the algorithm to terminate early if an interior maximum is found. If set to bound.tol=Inf, no early termination is attempted.

epsilon

Positive convergence tolerance. If \theta is a vector of estimates, convergence is declared when \sqrt{(\sum (\theta_{old} - \theta_{new})^2)}/ \sqrt{\sum (\theta_{old})^2} . This should be smaller than bound.tol.

maxit

integer giving the maximum number of EM algorithm iterations for a given parameterisation.

Details

This is used similarly to glm.control. If required, it may be internally passed to another function.

Value

A list of the three components: bound.tol, epsilon and maxit .