rmultivariate_normal

Generate sample from a multivariate normal distribution. The generator uses
a singular values decomposition to draw samples from a normal distribution
in the basis of the singular vector. Consequently, the covariance matrix
can be singular.

Statistical distribution in OOP (Object Oriented Programming) way.
This package proposes a R6 class interface to classic statistical
distribution, and new distributions can be easily added with the
class AbstractDist. A useful point is the generic fit() method for
each class, which uses a maximum likelihood estimation to find the
parameters of a dataset, see, e.g. Hastie, T. and al (2009)
<isbn:978-0-387-84857-0>. Furthermore, the rv_histogram class
gives a non-parametric fit, with the same accessors that for the
classic distribution. Finally, three random generators useful to
build synthetic data are given: a multivariate normal generator, an
orthogonal matrix generator, and a symmetric positive definite
matrix generator, see Mezzadri, F. (2007)
<arXiv:math-ph/0609050>.

Yoann Robin

ROOPSD

R Object Oriented Programming for Statistical Distribution

rmultivariate_normal function

<dl><dt>n</dt>
<dd>[integer] numbers of samples drawn</dd>
<dt>mean</dt>
<dd>[vector] mean of Normal law</dd>
<dt>cov</dt>
<dd>[matrix] covariance matrix</dd></dl>

Arguments

rmultivariate_normal — rmultivariate_normal

<dl>

<dt>n</dt>
<dd>[integer] numbers of samples drawn</dd>


<dt>mean</dt>
<dd>[vector] mean of Normal law</dd>


<dt>cov</dt>
<dd>[matrix] covariance matrix</dd>

</dl>

rmultivariate_normal: rmultivariate_normal

Description

Usage

Value

Arguments

Examples