internal_mlehelpers_for_distrMod: Internal helper functions for treating MCEstimators in package distrMod

Description

These functions are used internally by functions MCEstimator and MLEstimator in package ``distrMod''.

Usage

.negLoglikelihood(x, Distribution, ..., dropZeroDensity = TRUE)
.process.meCalcRes(res, PFam, trafo, res.name, call, asvar.fct, check.validity,
                   ..., toClass="", .withEvalAsVar = TRUE, x = NULL, nmsffx = "")
.callParamFamParameter(PFam, theta, idx, nuis, fixed)

Value

negLoglikelihood: the (numeric) value of the negative log likelihood evaluated at the data and the given distribution
.get.criterion.fct: a function as described in section ``details''
.process.meCalcRes: an object of class MCEstimate
.callParamFamParameter: an object of class ParamFamParameter or if necessary a corresponding subclass.

Arguments

x: numeric; the data at which to evaluate the negative log likelihood
Distribution: an object of class Distribution; the distribution at which to evaluate the negative log likelihood
...: in case of .negLoglikelihood simply to be able to use the general calling for the criterion function; in case of .process.meCalcRes further arguments to be passed to function asvar.fct
res: a list; the return value of mleCalc or mceCalc
PFam: an object of class ParamFamily; the parametric family at which to evaluate the MCE
trafo: the trafo matrix or a function returning it or NULL
res.name: the name of the corresponding estimator
call: the original call with which the estimate was produced
asvar.fct: a function producing an asymptotic covariance matrix or NULL.
check.validity: logical: shall return parameter value be checked for validity?
theta: parameter vector
idx: indices of the main part of the component
nuis: nuisance part of the parameter
fixed: fixed part of the parameter
.withEvalAsVar: logical: shall slot asVar be evaluated (if asvar.fct is given) or just the call be returned?
dropZeroDensity: logical of length 1; shall observations with density zero be dropped? Optimizers like optim require finite values, so get problems when negative loglikelihood is evaluated.
nmsffx: character: a potential suffix to be appended to the estimator name.
toClass: character: if not "" the name of a more specific return class.

Author

Peter Ruckdeschel peter.ruckdeschel@uni-oldenburg.de

Details

.negLoglikelihood uses the log -argument of the corresponding d-slot of the distribution if available; else produces log(d(Distribution)(x)).

.process.meCalcRes processes the resulting return value list of methods mceCalc and mleCalc to give a corresponding object of class MCEstimate.