31_em.ic: Information Criteria for Model-Based Clustering

In EMCluster: EM Algorithm for Model-Based Clustering of Finite Mixture Gaussian Distribution

Information Criteria for Model-Based Clustering

Description

These functions are tools for compute information criteria for the fitted models.

Usage

em.ic(x, emobj = NULL, pi = NULL, Mu = NULL, LTSigma = NULL,
      llhdval = NULL)
em.aic(x, emobj = NULL, pi = NULL, Mu = NULL, LTSigma = NULL)
em.bic(x, emobj = NULL, pi = NULL, Mu = NULL, LTSigma = NULL)
em.clc(x, emobj = NULL, pi = NULL, Mu = NULL, LTSigma = NULL)
em.icl(x, emobj = NULL, pi = NULL, Mu = NULL, LTSigma = NULL)
em.icl.bic(x, emobj = NULL, pi = NULL, Mu = NULL, LTSigma = NULL)

Arguments

x	the data matrix, dimension n\times p.
emobj	the desired model which is a list mainly contains pi, Mu, and LTSigma, usually a returned object from init.EM.
pi	the mixing proportion, length K.
Mu	the centers of clusters, dimension K\times p.
LTSigma	the lower triangular matrices of dispersion, K\times p(p+1)/2.
llhdval	the total log likelihood value of x given emobj.

Details

The em.ic calls all other functions to compute AIC (em.aic), BIC (em.bic), CLC (em.clc), ICL (em.icl), and ICL.BIC (em.icl.bic). All are useful information criteria for model selections, mainly choosing number of cluster.

Value

em.ic returns a list containing all other information criteria for given the data x and the desired model emobj.

Author(s)

Wei-Chen Chen [e-mail] and Ranjan Maitra

References

https://www.stat.iastate.edu/people/ranjan-maitra

See Also

init.EM.

Examples

library(EMCluster, quietly = TRUE)
x2 <- da2$da

emobj <- list(pi = da2$pi, Mu = da2$Mu, LTSigma = da2$LTSigma)
em.ic(x2, emobj = emobj)

EMCluster documentation built on Sept. 8, 2023, 5:55 p.m.