bdm::mgamma_fix Class Reference

Gamma random walk around a fixed point. More...

#include <libEF.h>

Inheritance diagram for bdm::mgamma_fix:

Inheritance graph
[legend]
Collaboration diagram for bdm::mgamma_fix:

Collaboration graph
[legend]

List of all members.

Public Member Functions

 mgamma_fix (const RV &rv, const RV &rvc)
 Constructor.
void set_parameters (double k0, vec ref0, double l0)
 Set value of k.
void condition (const vec &val)
 Update ep so that it represents this mpdf conditioned on rvc = cond.
void set_parameters (double k)
 Set value of k.
virtual vec samplecond (const vec &cond, double &ll)
 Returns a sample from the density conditioned on cond, $x \sim epdf(rv|cond)$.
virtual mat samplecond_m (const vec &cond, vec &ll, int N)
 Returns.
virtual double evallogcond (const vec &dt, const vec &cond)
 Shortcut for conditioning and evaluation of the internal epdf. In some cases, this operation can be implemented efficiently.
virtual vec evallogcond_m (const mat &Dt, const vec &cond)
 Matrix version of evallogcond.
RV _rvc () const
 access function
RV _rv () const
 access function
epdf_epdf ()
 access function
epdf_e ()
 access function

Protected Attributes

double l
 parameter l
vec refl
 reference vector
egamma epdf
 Internal epdf that arise by conditioning on rvc.
double k
 Constant $k$.
vec * _beta
 cache of epdf.beta
RV rv
 modeled random variable
RV rvc
 random variable in condition
epdfep
 pointer to internal epdf


Detailed Description

Gamma random walk around a fixed point.

Mean value, $\mu$, of this density is given by a geometric combination of rvc and given fixed point, $p$. $l$ is the coefficient of the geometric combimation

\[ \mu = \mu_{t-1} ^{l} p^{1-l}\]

Standard deviation of the random walk is proportional to one $k$-th the mean. This is achieved by setting $\alpha=k$ and $\beta=k/\mu$.

The standard deviation of the walk is then: $\mu/\sqrt(k)$.


Member Function Documentation

virtual vec bdm::mpdf::samplecond ( const vec &  cond,
double &  ll 
) [inline, virtual, inherited]

Returns a sample from the density conditioned on cond, $x \sim epdf(rv|cond)$.

Parameters:
cond is numeric value of rv
ll is a return value of log-likelihood of the sample.

Reimplemented in bdm::mprod.

References bdm::mpdf::condition(), bdm::mpdf::ep, bdm::epdf::evallog(), and bdm::epdf::sample().

Referenced by bdm::MPF< BM_T >::bayes(), bdm::PF::bayes(), and bdm::ArxDS::step().

virtual mat bdm::mpdf::samplecond_m ( const vec &  cond,
vec &  ll,
int  N 
) [inline, virtual, inherited]

Returns.

Parameters:
N samples from the density conditioned on cond, $x \sim epdf(rv|cond)$.
cond is numeric value of rv
ll is a return value of log-likelihood of the sample.

References bdm::mpdf::condition(), bdm::RV::count(), bdm::mpdf::ep, bdm::epdf::evallog(), bdm::mpdf::rv, and bdm::epdf::sample().


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

Generated on Fri Feb 6 19:50:14 2009 for mixpp by  doxygen 1.5.6