Package org.broadinstitute.hellbender.utils.mcmc
package org.broadinstitute.hellbender.utils.mcmc
-
ClassDescriptionMetropolis MCMC sampler using an adaptive step size that increases / decreases in order to decrease / increase acceptance rate to some desired value.Interface for tagging any class that represents a collection of datasets required to update posterior samples for Markov-Chain Monte Carlo sampling using samplers implementing the
ParameterSamplerinterface.Enumerates individual deciles.Represents a set of deciles.GibbsSampler<V extends Enum<V> & ParameterEnum,S extends ParameterizedState<V>, T extends DataCollection> Implements Gibbs sampling of a multivariate probability density function.MinibatchSliceSampler<DATA>Implements slice sampling of a continuous, univariate, unnormalized probability density function (PDF), which is assumed to be unimodal.Represents a parameter value with a namedParameterEnumkey.Interface for tagging an enum that represents the name of everyParametercomprising aParameterizedState.ParameterizedModel<V1 extends Enum<V1> & ParameterEnum,S1 extends ParameterizedState<V1>, T1 extends DataCollection> Represents a parameterized model.ParameterizedModel.GibbsBuilder<V2 extends Enum<V2> & ParameterEnum,S2 extends ParameterizedState<V2>, T2 extends DataCollection> Builder for constructing a ParameterizedModel to be Gibbs sampled usingGibbsSampler.Represents a mapped collection ofParameterobjects, i.e., named, ordered, enumerated keys associated with values of mixed type via a key -> key, value map.ParameterSampler<U,V extends Enum<V> & ParameterEnum, S extends ParameterizedState<V>, T extends DataCollection> Interface for generating random samples of aParametervalue, given anParameterizedStateand aDataCollection.Implements slice sampling of a continuous, univariate, unnormalized probability density function (PDF), which is assumed to be unimodal.