eEmp Class Reference

Weighted empirical density. More...

#include <libEF.h>

Inheritance diagram for eEmp:

[legend]

Collaboration diagram for eEmp:

[legend]

List of all members.

Public Member Functions
	eEmp (const RV &rv0)
void	set_parameters (const vec &w0, epdf *pdf0)
vec &	_w ()
	Potentially dangerous, use with care.
Array< vec > &	_samples ()
ivec	resample (RESAMPLING_METHOD method=SYSTEMATIC)
	Function performs resampling, i.e. removal of low-weight samples and duplication of high-weight samples such that the new samples represent the same density.
vec	sample ()
	Returns the required moment of the epdf.
vec	mean ()
	return expected value
virtual double	eval (const vec &val)
	Compute probability of argument val.
virtual double	evalpdflog (const vec &val)
	Compute log-probability of argument val.
Protected Attributes
int	n
	Number of particles.
vec	w
Array< vec >	samples
RV	rv

---

Detailed Description

Weighted empirical density.

Used e.g. in particle filters.

---

Member Function Documentation

vec eEmp::sample

(

)

[inline, virtual]

Returns the required moment of the epdf.

Returns a sample from the density,

Implements epdf.

---

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

• work/mixpp/bdm/stat/libEF.h
• work/mixpp/bdm/stat/libEF.cpp

---