File: [local] / OpenXM / src / R / r-packages / hgm / man / hgm.ncorthant.Rd (download)
Revision 1.2, Thu Apr 3 08:27:50 2014 UTC (10 years, 5 months ago) by tkoyama
Branch: MAIN
CVS Tags: RELEASE_1_3_1_13b Changes since 1.1: +6 -4
lines
hgm_ko_orthant now calls the Fortran's BLAS/Lapack,
and follows the standard manner calling the BLAS/Lapack from R.
|
% $OpenXM: OpenXM/src/R/r-packages/hgm/man/hgm.ncorthant.Rd,v 1.2 2014/04/03 08:27:50 tkoyama Exp $
\name{hgm.ncorthant}
\alias{hgm.ncorthant}
%- Also NEED an '\alias' for EACH other topic documented here.
\title{
The function hgm.ncorthant evaluates the orthant probability.
}
\description{
The function hgm.ncorthant evaluates the orthant probability,
which is the normalization constant of the multivariate normal distribution
restrcted to the first orthant.
}
\usage{
hgm.ncorthant(x,y,rk_step_size=1e-3)
}
%- maybe also 'usage' for other objects documented here.
\arguments{
\item{x}{}
\item{y}{
This function evaluates the orthant probability for the m dimensional
multivariate
normal distribution whose m by m covariance matrix and the mean vector
of size m are x and y respectively.
}
\item{rk_step_size}{
The step size for the Runge-Kutta method to apply the HGM.
}
}
\details{
The function hgm.ncorthant evaluates the orthant probability,
which is the normalization constant of the m-dimensional
multivariate normal distribution
restrcted to the first orthant.
It uses the holonomic gradient method (HGM) to evalute it.
The rank of the system of differential equations for the HGM is
2^m.
% \code{\link[RCurl]{postForm}}.
}
\value{
The output is the orthant probalibity.
}
\references{
Tamio Koyama, Akimichi Takemura,
Calculation of orthant probabilities
by the holonomic gradient method,
\url{http://arxiv.org/abs/1211.682}.
}
\author{
Tamio Koyama
}
\note{
%% ~~further notes~~
}
%% ~Make other sections like Warning with \section{Warning }{....} ~
\seealso{
%%\code{\link{oxm.matrix_r2tfb}}
}
\examples{
## =====================================================
## Example 1. Computing the orthant probability
## =====================================================
x <- matrix(c(15,26,23,19,
26,47,46,35,
23,46,65,38,
19,35,38,33), nrow =4)
y <- c(1,2,3,4)
hgm.ncorthant(x,y)
}
% Add one or more standard keywords, see file 'KEYWORDS' in the
% R documentation directory.
\keyword{ Normalization constant }
\keyword{ Holonomic gradient method }
\keyword{ HGM }
\keyword{ Orthant probability}