https://github.com/cran/fOptions
Tip revision: 6f9d6d063ca52f2494b9efd22298d2155e83de70 authored by Diethelm Wuertz on 08 August 1977, 00:00:00 UTC
version 220.10063
version 220.10063
Tip revision: 6f9d6d0
D1-LowDiscrepancy.Rd
\name{LowDiscrepancy}
\alias{LowDiscrepancy}
\alias{runif.halton}
\alias{rnorm.halton}
\alias{runif.sobol}
\alias{rnorm.sobol}
\alias{runif.pseudo}
\alias{rnorm.pseudo}
\title{Low Discrepancy Sequences}
\description{
A collection and description of functions to compute
Halton's and Sobol's low discrepancy sequences,
distributed in form of a uniform or normal distribution.
\cr
The functions are:
\tabular{ll}{
\code{runif.halton} \tab Uniform Halton sequence, \cr
\code{rnorm.halton} \tab Normal Halton sequence, \cr
\code{runif.sobol} \tab Uniform scrambled Sobol sequence, \cr
\code{rnorm.sobol} \tab Normal scrambled Sobol sequence, \cr
\code{runif.pseudo} \tab Uniform pseudo random numbers, \cr
\code{norma.pseudo} \tab Normal pseudo random numbers.}
}
\usage{
runif.halton(n, dimension, init)
rnorm.halton(n, dimension, init)
runif.sobol(n, dimension, init, scrambling, seed)
rnorm.sobol(n, dimension, init, scrambling, seed)
runif.pseudo(n, dimension, init)
rnorm.pseudo(n, dimension, init)
}
\arguments{
\item{dimension}{
an integer value, the dimension of the sequence. The
maximum value for the Sobol generator is 1111.
}
\item{init}{
a logical, if TRUE the sequence is initialized and
restarts, otherwise not. By default TRUE.
}
\item{n}{
an integer value, the number of random deviates.
}
\item{scrambling}{
an integer value, if 1, 2 or 3 the sequence is scrambled
otherwise not. If 1, Owen type type of scrambling is
applied, if 2, Faure-Tezuka type of scrambling, is
applied, and if 3, both Owen+Faure-Tezuka type of
scrambling is applied. By default 0.
}
\item{seed}{
an integer value, the random seed for initialization
of the scrambling process. By default 4711. On effective
if \code{scrambling>0}.
}
}
\value{
All generators return a numeric matrix of size \code{n}
by \code{dimension}.
}
\details{
\bold{Halton's Low Discrepancy Sequences:}
\cr\cr
Calculates a matrix of uniform or normal deviated halton low
discrepancy numbers.
\cr
\bold{Scrambled Sobol's Low Discrepancy Sequences:}
\cr\cr
Calculates a matrix of uniform and normal deviated Sobol low
discrepancy numbers. Optional scrambling of the sequence can
be selected.
\cr
\bold{Pseudo Random Number Sequence:}
\cr\cr
Calculates a matrix of uniform or normal distributed pseudo
random numbers. This is a helpful function for comparing
investigations obtained from a low discrepancy series with
those from a pseudo random number.
}
\note{
The global variables \code{runif.halton.seed} and
\code{runif.sobol.seed} save the status to restart the
generators. Note, that only one instance of a generators
can be run at the same time.
The ACM Algorithm 659 implemented to generate scrambled
Sobol sequences is under the License of the ACM restricted
for academic and noncommerical usage. Please consult the
ACM License agreement included in the \code{doc} directory.
}
\author{
P. Bratley and B.L. Fox for the Fortran Sobol Algorithm 659,\cr
S. Joe for the Fortran extension to 1111 dimensions,\cr
Diethelm Wuertz for the Rmetrics \R-port.
}
\references{
Bratley P., Fox B.L. (1988);
\emph{Algorithm 659: Implementing Sobol's Quasirandom
Sequence Generator},
ACM Transactions on Mathematical Software 14, 88--100.
Joe S., Kuo F.Y. (1998);
\emph{Remark on Algorithm 659: Implementing Sobol's Quaisrandom
Seqence Generator}.
}
\examples{
## SOURCE("fOptions.D1-LowDiscrepancy")
## *.halton -
xmpOptions("\nStart: Uniform Holton Numbers > ")
par(mfrow = c(2, 2), cex = 0.75)
runif.halton(n = 10, dimension = 5)
hist(runif.halton(n = 5000, dimension = 1), main = "Uniform Halton",
xlab = "x", col = "steelblue3", border = "white")
xmpOptions("\nNext: Normal Holton Numbers > ")
rnorm.halton(n = 10, dimension = 5)
hist(rnorm.halton(n = 5000, dimension = 1), main = "Normal Halton",
xlab = "x", col = "steelblue3", border = "white")
## *.sobol -
xmpOptions("\nNext: Uniform Sobol Numbers > ")
runif.sobol(n = 10, dimension = 5, scrambling = 3)
hist(runif.sobol(5000, 1, scrambling = 2), main = "Uniform Sobol",
xlab = "x", col = "steelblue3", border = "white")
xmpOptions("\nNext: Normal Sobol Numbers > ")
rnorm.sobol(n = 10, dimension = 5, scrambling = 3)
hist(rnorm.sobol(5000, 1, scrambling = 2), main = "Normal Sobol",
xlab = "x", col = "steelblue3", border = "white")
## *.pseudo -
xmpOptions("\nNext: Uniform Pseudo Random Numbers > ")
runif.pseudo(n = 10, dimension = 5)
rnorm.pseudo(n = 10, dimension = 5)
}
\keyword{programming}