#include <emix.h>
Public Member Functions | |
mprod (Array< mpdf * > mFacs) | |
Constructor from list of mFacs,. | |
double | evallogcond (const vec &val, const vec &cond) |
Shortcut for conditioning and evaluation of the internal epdf. In some cases, this operation can be implemented efficiently. | |
vec | samplecond (const vec &cond, double &ll) |
Returns the required moment of the epdf. | |
mat | samplecond (const vec &cond, vec &ll, int N) |
RV | getrv (bool checkoverlap=false) |
find common rv, flag | |
void | setrvc (const RV &rv, RV &rvc) |
common rvc of all mpdfs is written to rvc | |
virtual mat | samplecond_m (const vec &cond, vec &ll, int N) |
Returns. | |
virtual void | condition (const vec &cond) |
Update ep so that it represents this mpdf conditioned on rvc = cond. | |
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 | |
Protected Attributes | |
Array< epdf * > | epdfs |
pointers to epdfs - shortcut to mpdfs()._epdf() | |
Array< datalink_m2m * > | dls |
Data link for each mpdfs. | |
int | n |
Number of mpdfs in the composite. | |
Array< mpdf * > | mpdfs |
Elements of composition. | |
RV | rv |
modeled random variable | |
RV | rvc |
random variable in condition | |
epdf * | ep |
pointer to internal epdf |
Probability density in the form of Chain-rule decomposition: \[ f(x_1,x_2,x_3) = f(x_1|x_2,x_3)f(x_2,x_3)f(x_3) \] Note that
vec mprod::samplecond | ( | const vec & | cond, | |
double & | ll | |||
) | [inline, virtual] |
Returns the required moment of the epdf.
Returns a sample from the density conditioned on cond
, .
cond | is numeric value of rv | |
ll | is a return value of log-likelihood of the sample. |
Reimplemented from mpdf.
References RV::count(), dls, epdfs, compositepdf::mpdfs, compositepdf::n, and mpdf::rv.
RV compositepdf::getrv | ( | bool | checkoverlap = false |
) | [inherited] |
find common rv, flag
checkoverlap | modifies whether overlaps are acceptable |
References RV::add(), compositepdf::mpdfs, and compositepdf::n.
virtual mat mpdf::samplecond_m | ( | const vec & | cond, | |
vec & | ll, | |||
int | N | |||
) | [inline, virtual, inherited] |
Returns.
N | samples from the density conditioned on cond , . | |
cond | is numeric value of rv | |
ll | is a return value of log-likelihood of the sample. |
References mpdf::condition(), RV::count(), mpdf::ep, epdf::evallog(), mpdf::rv, and epdf::sample().