rmixGibbs makes one draw using the Gibbs Sampler for a mixture of multivariate normals. rmixGibbs is not designed to be called directly. Instead, use rnmixGibbs wrapper function.
rmixGibbs(y, Bbar, A, nu, V, a, p, z)a list containing:
draw of mixture probabilities
draw of indicators of each component
new draw of normal component parameters
data array where rows are obs
prior mean for mean vector of each norm comp
prior precision parameter
prior d.f. parm
prior location matrix for covariance prior
Dirichlet prior parms
prior prob of each mixture component
component identities for each observation -- "indicators"
Rob McCulloch (Arizona State University) and Peter Rossi (Anderson School, UCLA), perossichi@gmail.com.
This routine is a utility routine that does not check the input arguments for proper dimensions and type.
For further discussion, see Chapter 5 Bayesian Statistics and Marketing by Rossi, Allenby, and McCulloch.
rnmixGibbs