https://github.com/cran/fArma
Tip revision: 7099ae77cbaf0787ae181532d244398da9e1e4e2 authored by Rmetrics Core Team on 28 September 2009, 00:00:00 UTC
version 2100.76
version 2100.76
Tip revision: 7099ae7
LrdStatistics.Rd
\name{LongRangeDependence}
\alias{LongRangeDependence}
\alias{fgnTrueacf}
\alias{fgnTruefft}
\alias{fgnStatsSlider}
\alias{farimaTrueacf}
\alias{farimaTruefft}
\alias{farimaStatsSlider}
\title{Statistics of the True LRD Process}
\description{
A collection and description of functions
to investigate the true statistics of the
long range dependence or long memory behavior
of an univariate time series process.
\cr
The Functions are:
Functions to model the true autocorrelation function and spectrum:
\tabular{ll}{
\code{fgnTrueacf} \tab Returns true FGN covariances, \cr
\code{fgnTruefft} \tab returns true FGN fast Fourier transform, \cr
\code{fgnStatsSlider} \tab returns a plot of true FGN Statistics, \cr
\code{farimaTrueacf} \tab returns true FARIMA covariances, \cr
\code{farimaTruefft} \tab returns true FARIMA fast Fourier transform, \cr
\code{farimaStatsSlider} \tab returns a plot of true FARIMA Statistics. }
}
\usage{
fgnTrueacf(n = 100, H = 0.7)
fgnTruefft(n = 100, H = 0.7)
fgnStatsSlider()
farimaTrueacf(n = 100, H = 0.7)
farimaTruefft(n = 100, H = 0.7)
farimaStatsSlider()
}
\arguments{
\item{H}{
the Hurst exponent, a numeric value between 0.5 and 1,
by default 0.7.
}
\item{n}{
number of data points to be simulated, a numeric value,
by default 100.
}
}
\value{
\code{fgnTrueacf}\cr
\code{farimaTrueacf}\cr
return the true covariance of an FGN or FARIMA time series process.
\cr
\code{fgnTruefft}\cr
\code{farimaTruefft}\cr
return the true spectrum of an FGN or FARIMA time series process.
\cr
fgnStatsSlider()\cr
farimStatsSlider()\cr
interactively display the true covariance and the true spectrum
of an FGN or FARIMA time series process.
}
\details{
\bold{Functions to Model True Correlations and Spectrum:}
\cr
The functions \code{fgnTrueacf} and \code{farimaTrueacf} return the
true covariances of an FGN and Gaussian FARIMA(0,d,0) time
series process.
The functions \code{fgnTruefft} and \code{farimaTruefft} return the
true fast Fourier transform of an FGN and Gaussian FARIMA(0,d,0)
time series process.
The R functions are implemented from SPlus code written by
J. Beran [1994].
}
\references{
Beran J. (1992);
\emph{Statistics for Long-Memory Processes},
Chapman and Hall, New York, 1994.
}
\author{
J. Beran, ported by Maechler, code as listed in the Appendix of his Book, \cr
Diethelm Wuertz for the Rmetrics \R-port.
}
\examples{
## fgnTrueacf -
fgnTrueacf(n = 20, H = 0.8)
## fgnTruefft -
fgnTruefft(n = 20, H = 0.8)
## farimaTrueacf -
farimaTrueacf(n = 20, H = 0.8)
## farimaTruefft -
farimaTruefft(n = 20, H = 0.8)
}
\keyword{models}