heavy.control: Set control parameters

In heavy: Robust Estimation Using Heavy-Tailed Distributions

Description

Allows users to set control parameters for routines available in heavy.

Usage

heavy.control(maxIter = 2000, tolerance = 1e-6, fix.shape = FALSE,
  ndraws = 500, algorithm = c("EM", "NEM"), ncycles = 5)

Arguments

maxIter	maximum number of iterations. The default is 2000.
tolerance	the relative tolerance in the iterative algorithm.
fix.shape	whether the shape parameters should be kept fixed in the fitting processes. The default is fix.shape = FALSE. Currently, only is available for the Student-t and slash distributions.
ndraws	independent draws for Monte Carlo integration. The default is 500.
algorithm	character string specifying the algorithm to use. The default algorithm is an EM algorithm. Other possible value is "NEM" for the nested EM algorithm.
ncycles	number of cycles used in the nested EM algorithm, not used if algorithm="EM". The default is 5.

Value

A list of control arguments to be used in a call to the fitter (i.e., heavyFit, heavyGrubbs, heavyLm, heavyLme or heavyPS functions).

A call to heavy.control can be used directly in the control argument of the call to the fitter.

See Also

heavyFit, heavyGrubbs, heavyLm, heavyLme, heavyPS

Examples

ctrl <- heavy.control(maxIter = 200, tol = 1e-04, ndraws = 9000)
data(dental)
heavyLme(distance ~ age * Sex, random = ~ age, groups = ~ Subject,
  data = dental, control = ctrl)

heavy documentation built on Oct. 30, 2019, 9:48 a.m.