enorm< sq_T > Class Template Reference

Gaussian density with positive definite (decomposed) covariance matrix. More...

#include <libEF.h>

Inheritance diagram for enorm< sq_T >:

Inheritance graph
[legend]
Collaboration diagram for enorm< sq_T >:

Collaboration graph
[legend]

List of all members.

Public Member Functions

 enorm (RV &rv)
 Default constructor.
void set_parameters (const vec &mu, const sq_T &R)
 Set mean value mu and covariance R.
void tupdate (double phi, mat &vbar, double nubar)
 tupdate in exponential form (not really handy)
void dupdate (mat &v, double nu=1.0)
 dupdate in exponential form (not really handy)
vec sample () const
 Returns the required moment of the epdf.
mat sample (int N) const
 TODO is it used?
double eval (const vec &val) const
 Compute probability of argument val.
double evalpdflog (const vec &val) const
 Compute log-probability of argument val.
vec mean () const
 return expected value
vec * _mu ()
 returns a pointer to the internal mean value. Use with Care!
void _R (sq_T *&pR, sq_T *&piR)
 returns pointers to the internal variance and its inverse. Use with Care!
void _cached (bool what)
 set cache as inconsistent
RV _rv () const
 access function

Protected Attributes

vec mu
 mean value
sq_T R
 Covariance matrix in decomposed form.
sq_T _iR
 Cache: _iR = inv(R);.
bool cached
 indicator if _iR is chached
int dim
 dimension (redundant from rv.count() for easier coding )
RV rv
 Identified of the random variable.


Detailed Description

template<class sq_T>
class enorm< sq_T >

Gaussian density with positive definite (decomposed) covariance matrix.

More?...


Member Function Documentation

template<class sq_T>
vec enorm< sq_T >::sample (  )  const [inline, virtual]

Returns the required moment of the epdf.

Returns a sample from the density, $x \sim epdf(rv)$

Implements epdf.


The documentation for this class was generated from the following file:
Generated on Wed Mar 12 16:15:49 2008 for mixpp by  doxygen 1.5.3