EMMIXskew (version 1.0.3)

getICL: The ICL criterion

Description

Calculate the Integrated Completed Likelihood(ICL) criterion

Usage

getICL(x, n, p, g, distr, ncov, pro, mu, sigma, dof, delta, clust)

Arguments

x

An n by p data matrix

n

The total number of points

p

Dimension of data

g

the number of components of the mixture model

distr

A three letter string indicating the type of distribution to be fit.

ncov

A small integer indicating the type of covariance structure.

pro

A vector of mixing proportions

mu

A numeric matrix with each column corresponding to the mean

sigma

An array of dimension (p,p,g) with first two dimension corresponding covariance matrix of each component

dof

A vector of degrees of freedom for each component

delta

A p by g matrix with each column corresponding to a skew parameter vector

clust

A vector of partition

Value

ICL

ICL value

References

Biernacki C. Celeux G., and Govaert G. (2000). Assessing a Mixture Model for Clustering with the integrated Completed Likelihood. IEEE Transactions on Pattern Analysis and Machine Intelligence. 22(7). 719-725.

Examples

# NOT RUN {
n1=300;n2=300;n3=400;
nn <-c(n1,n2,n3)
n=1000
p=2
ng=3


sigma<-array(0,c(2,2,3))
for(h in 2:3) sigma[,,h]<-diag(2)
sigma[,,1]<-cbind( c(1,0),c(0,1))
mu  <- cbind(c(4,-4),c(3.5,4),c( 0, 0))

pro   <- c(0.3,0.3,0.4)

distr="mvn"
ncov=3

#first we generate a data set
set.seed(111) #random seed is set 
dat <- rdemmix(nn,p,ng,distr,mu,sigma,dof=NULL,delta=NULL)

#start from initial partition
clust<- rep(1:ng,nn)
obj <- EmSkewfit1(dat, ng, clust, distr, ncov, itmax=1000,epsilon=1e-4)

getICL(dat,n,p,ng, distr,ncov,obj$pro,obj$mu,obj$sigma,obj$dof,
obj$delta,obj$clust)

# }