egiw Class Reference

Gauss-inverse-Wishart density stored in LD form. More...

#include <libEF.h>

Inheritance diagram for egiw:

Inheritance graph
[legend]
Collaboration diagram for egiw:

Collaboration graph
[legend]

List of all members.

Public Member Functions

 egiw (RV rv, mat V0, double nu0=-1.0)
 Default constructor, if nu0<0 a minimal nu0 will be computed.
 egiw (RV rv, ldmat V0, double nu0=-1.0)
 Full constructor for V in ldmat form.
vec sample () const
 Returns a sample, $x$ from density $epdf(rv)$.
vec mean () const
 return expected value
void mean_mat (mat &M, mat &R) const
double evallog_nn (const vec &val) const
 In this instance, val= [theta, r]. For multivariate instances, it is stored columnwise val = [theta_1 theta_2 ... r_1 r_2 ].
double lognc () const
 logarithm of the normalizing constant, $\mathcal{I}$
ldmat_V ()
 returns a pointer to the internal statistics. Use with Care!
const ldmat_V () const
 returns a pointer to the internal statistics. Use with Care!
double & _nu ()
 returns a pointer to the internal statistics. Use with Care!
const double & _nu () const
void pow (double p)
 Power of the density, used e.g. to flatten the density.
virtual void dupdate (mat &v)
 TODO decide if it is really needed.
virtual double evallog (const vec &val) const
 Evaluate normalized log-probability.
virtual vec evallog (const mat &Val) const
 Evaluate normalized log-probability for many samples.
virtual mat sample_m (int N) const
 Returns N samples from density $epdf(rv)$.
virtual vec evallog_m (const mat &Val) const
 Compute log-probability of multiple values argument val.
virtual mpdfcondition (const RV &rv) const
 Return conditional density on the given RV, the remaining rvs will be in conditioning.
virtual epdfmarginal (const RV &rv) const
 Return marginal density on the given RV, the remainig rvs are intergrated out.
const RV_rv () const
 access function, possibly dangerous!
void _renewrv (const RV &in_rv)
 modifier function - useful when copying epdfs

Protected Attributes

ldmat V
 Extended information matrix of sufficient statistics.
double nu
 Number of data records (degrees of freedom) of sufficient statistics.
int xdim
 Dimension of the output.
int nPsi
 Dimension of the regressor.
RV rv
 Identified of the random variable.


Detailed Description

Gauss-inverse-Wishart density stored in LD form.

For $p$-variate densities, given rv.count() should be $p\times$ V.rows().


The documentation for this class was generated from the following files:

Generated on Thu Dec 4 14:42:20 2008 for mixpp by  doxygen 1.5.6