AM_emp_bayes_uninorm

The data y. If y is univariate, a vector is expected. Otherwise, y should be a matrix.

a positive value (default=1) such that marginally E(\(\mu\)) = \(s^2\)*scEmu, where \(s^2\) is the
sample variance.

scEmu

a positive value (default=3) such that marginally E(\(\sigma^2\)) = \(s^2\)*scEsig2, where \(s^2\) is the
sample variance.

scEsig2

The coefficient of variation of \(\sigma^2\) (default=3).

CVsig2

This function computes the hyperparameters of a Normal Inverse-Gamma distribution using an empirical Bayes approach.
More information about how these hyperparameters are determined can be found here:
Bayes and empirical Bayes: do they merge? petrone2012bayesAntMAN.

Fits finite Bayesian mixture models with a random number of components. The MCMC algorithm implemented is based on point processes as proposed by Argiento and De Iorio (2019) <arXiv:1904.09733> and offers a more computationally efficient alternative to reversible jump. Different mixture kernels can be specified: univariate Gaussian, multivariate Gaussian, univariate Poisson, and multivariate Bernoulli (latent class analysis). For the parameters characterising the mixture kernel, we specify conjugate priors, with possibly user specified hyper-parameters. We allow for different choices for the prior on the number of components: shifted Poisson, negative binomial, and point masses (i.e. mixtures with fixed number of components).

AM_emp_bayes_uninorm: compute the hyperparameters of an Normal-Inverse-Gamma distribution using an empirical Bayes approach

Description

Usage

Arguments

Value