telescope (version 0.2-1)

Bayesian Mixtures with an Unknown Number of Components

Description

Fits Bayesian finite mixtures with an unknown number of components using the telescoping sampler and different component distributions. For more details see Frühwirth-Schnatter et al. (2021) .

Copy Link

Version

Install

install.packages('telescope')

Monthly Downloads

114

Version

0.2-1

License

GPL-2

Maintainer

Gertraud Malsiner-Walli

Last Published

August 18th, 2025

Functions in telescope (0.2-1)

sampleAlpha

Sample alpha conditional on partition and K using an Metropolis-Hastings step with log-normal proposal.

plotScatter

Pairwise scatter plots of the data.

priorOnAlpha_spec

Specify prior on \(\alpha\).

priorOnK_spec

Specify prior on \(K\).

identifyMixture

Solve label switching and identify mixture.

priorOnE0_spec

Specify prior on e0.

identifyLCAMixture

Solve label switching and identify mixture for a mixture of LCA models.

plotBubble

Plot multivariate categorical data.

sampleLCA

Telescoping sampling of the LCA model where a prior on the number of components K is specified.

sampleMultNormMixture

Telescoping sampling of a Bayesian finite multivariate Gaussian mixture where a prior on the number of components is specified.

samplePoisMixture

Telescoping sampling of a Bayesian finite Poisson mixture with a prior on the number of components K.

sampleUniNormMixture

Telescoping sampling of a Bayesian finite univariate Gaussian mixture where a prior on the number of components K is specified.

sampleLCAMixture

Telescoping sampling of the mixture of LCA models where a prior on the number of components K is specified.

sampleE0

Sample e0 conditional on partition and K using an Metropolis-Hastings step with log-normal proposal.

sampleK_e0

Sample K conditional on e0 (fixed or random, but not depending on K).

SimData

Simulated multivariate binary data

sampleK_alpha

Sample K conditional on \(\alpha\) where \(e0 = \alpha/K\).