NAME

mv_gaussian_rand - Samples a gaussian random vector

SYNOPSIS

#include "sample/sample_gauss.h"

Example compile flags (system dependent):
  -DLINUX_X86_64 -DLINUX_X86_64_OPTERON  -DGNU_COMPILER 
   -I/home/kobus/include
   -L/home/kobus/misc/load/linux_x86_64_opteron -L/usr/lib/x86_64-linux-gnu
  -lKJB                               -lfftw3  -lgsl -lgslcblas -ljpeg  -lSVM -lstdc++                    -lpthread -lSLATEC -lg2c    -lacml -lacml_mv -lblas -lg2c      -lncursesw 


int mv_gaussian_rand
(
	Vector **sample,
	const Vector *mean,
	const Matrix *covar_mat
);

DESCRIPTION

This routine generates a normally-distributed vector of with mean 'mean' and covariance matrix 'covar_mat', where 'covar_mat' is positive-definite. For the special case where the covariance is diagonal, use the much faster routine mv_ind_gaussian_rand(). This routine uses kjb_rand().

RETURNS

Returns ERROR on failure, setting the the errors string accordingly, and NO_ERROR otherwise.

NOTE

It obtains a standard gaussian vector using mv_std_gaussian_rand and uses the Cholesky decomposition method to convert it into one with the specified mean and covariance matrix. The first argument is the adress of the target vector. If the target vector itself is NULL, then a vector of the appropriate size is created. If the target vector is the wrong size, it is resized. Finally, if it is the right size, then the storage is recycled, as is.

gauss_rand

DISCLAIMER

This software is not adequatedly tested. It is recomended that results are checked independantly where appropriate.

AUTHOR

Ernesto Brau

DOCUMENTER