Package dev.nm.stat.random.rng.multivariate.mcmc.proposalfunction

Class GaussianProposalFunction

java.lang.Object

dev.nm.analysis.function.rn2rm.AbstractRealVectorFunction

dev.nm.stat.random.rng.multivariate.mcmc.proposalfunction.ProposalFunction

dev.nm.stat.random.rng.multivariate.mcmc.proposalfunction.GaussianProposalFunction

All Implemented Interfaces:

Function<Vector,Vector>, RealVectorFunction

Direct Known Subclasses:

HybridMCMCProposalFunction

public class GaussianProposalFunction
extends ProposalFunction

A proposal generator where each perturbation is a random vector, where each element is drawn from a standard Normal distribution, multiplied by a scale matrix.

Nested Class Summary

Nested classes/interfaces inherited from interface dev.nm.analysis.function.Function

Function.EvaluationException

Constructor Summary

Constructors

Constructor	Description
GaussianProposalFunction(double[] sigma, RandomLongGenerator uniform)	Constructs a Gaussian proposal function.
GaussianProposalFunction(double sigma, int size, RandomLongGenerator uniform)	Constructs a Gaussian proposal function.
GaussianProposalFunction(Matrix scale, RandomLongGenerator uniform)	Constructs a Gaussian proposal function.

Method Summary

Modifier and Type	Method	Description
Vector	evaluate(Vector x)	Evaluate the function f at x, where x is from the domain.

Methods inherited from class dev.nm.analysis.function.rn2rm.AbstractRealVectorFunction

dimensionOfDomain, dimensionOfRange

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

GaussianProposalFunction

public GaussianProposalFunction(Matrix scale,
 RandomLongGenerator uniform)

Constructs a Gaussian proposal function.

Parameters:

scale - the scale matrix by which to multiply the standard Normal vector

uniform - a RandomLongGenerator

GaussianProposalFunction

public GaussianProposalFunction(double[] sigma,
 RandomLongGenerator uniform)

Constructs a Gaussian proposal function. The scale matrix is a diagonal matrix, where the elements along the diagonal correspond to the given vector.

Parameters:

sigma - the standard deviations of the individual variables

uniform - a RandomLongGenerator

GaussianProposalFunction

public GaussianProposalFunction(double sigma,
 int size,
 RandomLongGenerator uniform)

Constructs a Gaussian proposal function. The scale matrix is the identity matrix multiplied by the given constant, sigma, the standard deviation. The components have no covariance.

Parameters:

sigma - the standard deviation

size - the size of proposals

uniform - a RandomLongGenerator

Method Details

evaluate

public Vector evaluate(Vector x)

Description copied from interface: Function

Evaluate the function f at x, where x is from the domain.

Parameters:

x - x

Returns:

f(x)