https://github.com/cran/dse
Tip revision: f9aa6f7ec42024ca88a37a5e6984bada0a8d3891 authored by Paul Gilbert on 07 March 2013, 08:03:12 UTC
version 2013.3-2
version 2013.3-2
Tip revision: f9aa6f7
forecastCovEstimatorsWRTtrue.Rd
\name{forecastCovEstimatorsWRTtrue}
\alias{forecastCovEstimatorsWRTtrue}
\alias{is.forecastCovEstimatorsWRTtrue}
\title{Compare Forecasts Cov Relative to True Model Output}
\description{Compare covariance of the forecasts less the true model output}
\usage{
forecastCovEstimatorsWRTtrue(true.model, rng=NULL,
simulation.args=NULL,
est.replications = 2, pred.replications = 2,
discard.before = 10, horizons = 1:12, quiet =FALSE,
estimation.methods=NULL, compiled=.DSEflags()$COMPILED)
%% Spawn=if (exists(".SPAWN")) .SPAWN else FALSE
is.forecastCovEstimatorsWRTtrue(obj)
}
\arguments{
\item{true.model}{An object of class TSmodel.}
\item{estimation.methods}{A list as used by estimateModels.}
\item{simulation.args}{an arguments to be passed to simulate.}
\item{est.replications}{An arguments to be passed to simulate.}
\item{pred.replications}{An arguments to be passed to simulate.}
\item{discard.before}{
An integer indicating the number of points in the
beginning of forecasts to discard for calculating covariances.}
\item{horizons}{Horizons for which forecast covariance should be calculated.}
\item{rng}{If specified then it is used to set RNG.}
%% \item{Spawn}{If TRUE then Splus For loops are used.}
\item{quiet}{If TRUE then some messages are not printed.}
\item{compiled}{a logical indicating if the compiled version of the code
should be used. (FALSE would typically only be used for debugging.)}
\item{obj}{an object.}
}
\value{
The returned results has element
\code{forecastCov.true, forecastCov.zero, forecastCov.trend} containing
covariances averaged over estimation replications and simulation
replications (forecasts will not change but simulated data will).
\code{forecastCov} a list of the same length as estimation.methods with each
element containing covariances averaged over estimation replications
and simulation replications.
\code{estimatedModels} a list of length est.replications, with each elements as
returned by estimateModels, thus each element has \code{multi.model} as a
subelement containing models for different estimation techniques.
So, eg. \code{estimatedModels[[2]]$multi.model[[1]]} in the result will
be the model from the first estimation technique in the second replication.
}
\details{
Calculate the forecasts cov of models estimated from simulations of
true.model with estimation methods indicated by estimation.methods (see
estimateModels).
This function makes multiple calls to forecastCovWRTtrue.
}
\seealso{
\code{\link{forecastCovWRTtrue}}
\code{\link{forecastCovEstimatorsWRTdata}}
}
\examples{
data("eg1.DSE.data.diff", package="dse")
true.model <- estVARXls(eg1.DSE.data.diff) # just to have a starting model
z <- forecastCovEstimatorsWRTtrue(true.model,
estimation.methods=list(estVARXls=list(max.lag=4)))
}
\concept{DSE}
\keyword{ts}