BIE::GaussTestLikelihoodFunctionMulti Class Reference

A "user-defined" likelihood function for testing. More...

#include <GaussTestLikelihoodFunctionMulti.h>

Inheritance diagram for BIE::GaussTestLikelihoodFunctionMulti:

Collaboration diagram for BIE::GaussTestLikelihoodFunctionMulti:

List of all members.

Public Member Functions

GaussTestLikelihoodFunctionMulti ()

Null constructor.

GaussTestLikelihoodFunctionMulti (int Ptwo, int N0, int Levels)

Constructor with number of bins given by 2 to the power.

GaussTestLikelihoodFunctionMulti (int Ptwo, int N0, int Levels, vector< double > *cen0, vector< double > *var0, vector< double > *wgt0)

Constructor with number of bins given by 2 to the power.

GaussTestLikelihoodFunctionMulti (int N0, int Levels)

Constructor with for point likelihood function with a sample size of.

GaussTestLikelihoodFunctionMulti (int N0, int Levels, vector< double > *cen0, vector< double > *var0, vector< double > *wgt0)

Constructor for a point likelihood function with a sample size of.

void SetLevels (int n)

Set number levels.

void SetDim (int n)

Set data dimension (currently 1 or 2).

void PrintData ()

Print data to a file for the current level.

double LikeProb (std::vector< double > &z, SampleDistribution *sd, double norm, Tile *t, State *s, int indx)

This is likelihood function.

string ParameterDescription (int i)

Label parameters. Scheduled for removal.

Protected Member Functions

void makeSyntheticData ()

Make the synthetic binned data.

void makeSyntheticPointData ()

Make the synthetic point data.

void makeArrays ()

Make data arrays.

double LocalLikelihood (State *s)

This is likelihood function.

Friends

class boost::serialization::access

Detailed Description

A "user-defined" likelihood function for testing.

By default, the "data" is the combination of two one-dimensional Gaussians, one at 0.2 with variance of 0.03 and one at 0.9 with variance of 0.03 with 50% weights each.

The default model, including the number of components in the mixture, may be changed at construction.

The variance may be modeled or fixed (using the SetDim member).

This model is similar to GaussTestLikelihoodFunction but this version of the model allows data aggregation by powers of two and multiple level resolution. The global variable current_level sets the number of bins in LikeProb.

Constructor & Destructor Documentation

BIE::GaussTestLikelihoodFunctionMulti::GaussTestLikelihoodFunctionMulti	(	int	Ptwo,
		int	N0,
		int	Levels
	)

Constructor with number of bins given by 2 to the power.

Parameters:

	Ptwo	and a sample size of
	N0	points and aggregation up to
	Levels	times.

BIE::GaussTestLikelihoodFunctionMulti::GaussTestLikelihoodFunctionMulti	(	int	Ptwo,
		int	N0,
		int	Levels,
		vector< double > *	cen0,
		vector< double > *	var0,
		vector< double > *	wgt0
	)

Constructor with number of bins given by 2 to the power.

Parameters:

	Ptwo	and a sample size of
	N0	points and aggregation up to
	Levels	times. Vectors
	cen0,@param	var0, and
	wgt0	are the centers, variance values and weight values for the sampled model. The number of components is determined from the rank of the input vectors (which must agree!)

BIE::GaussTestLikelihoodFunctionMulti::GaussTestLikelihoodFunctionMulti	(	int	N0,
		int	Levels
	)

Constructor with for point likelihood function with a sample size of.

Parameters:

	N0	points and aggregation up to
	Levels	times.

BIE::GaussTestLikelihoodFunctionMulti::GaussTestLikelihoodFunctionMulti	(	int	N0,
		int	Levels,
		vector< double > *	cen0,
		vector< double > *	var0,
		vector< double > *	wgt0
	)

Constructor for a point likelihood function with a sample size of.

Parameters:

	N0	points and aggregation up to
	Levels	times. Vectors
	cen0,@param	var0, and
	wgt0	are the centers, variance values and weight values for the sampled model. The number of components is determined from the rank of the input vectors (which must agree!)

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

/home/weinberg/src/BIE/include/GaussTestLikelihoodFunctionMulti.h