bmm.posterior.predictive.density: bmm.posterior.predictive.density: Calculate the posterior...

In genome/bmm: Variational Bayesian approach to fitting mixtures of beta, binomial, or Gaussian distributions

bmm.posterior.predictive.density: Calculate the posterior predictive density.

Description

Calculate the posterior predictive density at a point x in a single dimension across all components

Usage

  bmm.posterior.predictive.density(x, mu, alpha, nu, beta, pi, num.samples = 1000)

Arguments

x	the scalar at which to evaluate the posterior predictive density
mu	an N.c vector holding the shape parameter for each of the N.c components, which governs the gamma prior distribution over that component's u parameter.
alpha	an N.c vector holding the rate (i.e., inverse scale) parameter for each of the N.c components, which governs the gamma prior distribution over that component's u parameter.
nu	an N.c vector holding the shape parameter for each of the N.c components, which governs the gamma prior distribution over that component's v parameter.
beta	an N.c vector holding the rate (i.e., inverse scale) parameter for each of the N.c components, which governs the gamma prior distribution over that component's v parameter.
pi	an N.c vector holding the mixing coefficients giving the weight of each of the N.c components
num.samples	the number of samples to use in performing the numerical evaluation of the predictive density

Value

the posterior preditive density at x summed across all components

genome/bmm documentation built on Aug. 4, 2022, 8:01 a.m.