gov.sandia.cognition.statistics.bayesian

Interface BayesianEstimatorPredictor<ObservationType,ParameterType,PosteriorType extends Distribution<? extends ParameterType>>

Type Parameters:

ObservationType - Observations from the ConditionalType that are used to estimate the parameters of the distribution.

ParameterType - Type of parameter estimated by this algorithm, which is used to parameterize the conditional distribution.

PosteriorType - Type of posterior Distribution, which describes the uncertainty of the parameters after we have incorporated the observations.

All Superinterfaces:

BatchLearner<java.util.Collection<? extends ObservationType>,PosteriorType>, BayesianEstimator<ObservationType,ParameterType,PosteriorType>, java.lang.Cloneable, CloneableSerializable, java.io.Serializable

All Known Subinterfaces:

ConjugatePriorBayesianEstimatorPredictor<ObservationType,ParameterType,ConditionalType,BeliefType>

All Known Implementing Classes:

BinomialBayesianEstimator, ExponentialBayesianEstimator, MultinomialBayesianEstimator, MultivariateGaussianMeanBayesianEstimator, MultivariateGaussianMeanCovarianceBayesianEstimator, PoissonBayesianEstimator, UnivariateGaussianMeanBayesianEstimator, UnivariateGaussianMeanVarianceBayesianEstimator

public interface BayesianEstimatorPredictor<ObservationType,ParameterType,PosteriorType extends Distribution<? extends ParameterType>>
extends BayesianEstimator<ObservationType,ParameterType,PosteriorType>

A BayesianEstimator that can also compute the predictive distribution of new data given the posterior.

Since:

3.0

Author:

Kevin R. Dixon

Method Summary

Modifier and Type	Method and Description
ComputableDistribution<ObservationType>	createPredictiveDistribution(PosteriorType posterior) Creates the predictive distribution of new data given the posterior.

Methods inherited from interface gov.sandia.cognition.learning.algorithm.BatchLearner

learn

Methods inherited from interface gov.sandia.cognition.util.CloneableSerializable

clone

Method Detail

createPredictiveDistribution

ComputableDistribution<ObservationType> createPredictiveDistribution(PosteriorType posterior)

Creates the predictive distribution of new data given the posterior. This is equivalent to evaluating the integral of: p( newdata | data ) = integral( conditional( newdata | data, parameters ) * p( parameters | data ) dparameters )

Parameters:

posterior - Posterior distribution from which to compute the predictive posterior.

Returns:

Predictive distribution of new data given the observed data.