pmclust (version 0.2-0)

One Step of EM algorithm: One EM Step for GBD

Description

One EM step only for model-based clustering of finite mixture Gaussian models with unstructured dispersions. This is a core function of em.step.

em.onestep.dmat is a ddmatrix version of em.onestep.

Usage

em.onestep(PARAM)
  em.onestep.dmat(PARAM)

Arguments

PARAM

an original set of parameters generated by set.global.

Value

This function is one EM step. The global variables will be updated and a new PARAM will be returned. See the help page of PARAM or PARAM.org for details.

Details

A global variable called X.spmd should exist in the .pmclustEnv environment, usually the working environment. The X.spmd is the data matrix to be clustered, and this matrix has a dimension N.spmd by p.

The PARAM will be a local variable for the current iteration inside em.onestep, and this variable is a list containing all parameters related to models. This function also updates in the parameters by the EM algorithm, and return a new PARAM for the next iteration. The details of list elements are initially generated by set.global.

References

Programming with Big Data in R Website: http://r-pbd.org/

See Also

set.global, e.step, m.step.

Examples

# NOT RUN {
# This is a core function for em.step()
# see the source code for details.
# }