Simulate Data Using Mixture Models

Description

Generate random number from specified mixture models, including univariate and multivariate Normal distribution, t-distribution, Skew Normal distribution, and Skew t-distribution.

Usage

rdemmix(nvect,p,g,distr,    mu,sigma,dof=NULL,delta=NULL)
rdemmix2(n,   p,g,distr,pro,mu,sigma,dof=NULL,delta=NULL)
rdemmix3(n,   p,g,distr,pro,mu,sigma,dof=NULL,delta=NULL)

Arguments

Details

The distribution type, determined by the distr parameter, which may take any one of the following values: "mvn" for a multivariate normal, "mvt" for a multivariate t-distribution, "msn" for a multivariate skew normal distribution and "mst" for a multivariate skew t-distribution. pro, a numeric vector of the mixing proportion of each component; mu, a p by g matrix with each column as its corresponding mean; sigma, a three dimensional p by p by g array with its jth component matrix (p,p,j) as the covariance matrix for jth component of mixture models; dof, a vector of degrees of freedom for each component; delta, a p by g matrix with its columns corresponding to skew parameter vectors.

Value

both rdemmix and rdemmix2 return an n by p numeric matrix of generated data;

rdemmix3 gives a list with components data, the generated data, and cluster, the clustering of data.

References

McLachlan G.J. and Krishnan T. (2008). The EM Algorithm and Extensions (2nd). New Jersay: Wiley.

McLachlan G.J. and Peel D. (2000). Finite Mixture Models. New York: Wiley.

See Also

rdmvn,rdmvt,rdmsn, rdmst.

Examples

#specify the dimension of data, and number of clusters
#the number of observations in each cluster
n1=300;n2=300;n3=400;
nn<-c(n1,n2,n3)

p=2
g=3



#specify the distribution
distr <- "mvn"

#specify mean and covariance matrix for each component

sigma<-array(0,c(2,2,3))
for(h in 2:3) sigma[,,h]<-diag(2)
sigma[,,1]<-cbind( c(1,-0.1),c(-0.1,1))
mu  <- cbind(c(4,-4),c(3.5,4),c( 0, 0))

#reset the random seed 
set.seed(111) 
#generate the dataset
dat <- rdemmix(nn,p,g,distr,    mu,sigma)



# alternatively one can use
pro   <- c(0.3,0.3,0.4)
n=1000
set.seed(111)
dat <- rdemmix2(n,p,g,distr,pro,mu,sigma)
plot(dat)

# and 

set.seed(111)
dobj <- rdemmix3(n,p,g,distr,pro,mu,sigma)
plot(dobj$data)


#other distributions such as "mvt","msn", and "mst".

#t-distributions

dof    <- c(3,5,5)
dat <- rdemmix2(n,p,g,"mvt",pro,mu,sigma,dof)
plot(dat)

#Skew Normal distribution
delta <- cbind(c(3,3),c(1,5),c(-3,1))
dat <- rdemmix2(n,p,g,"msn",pro,mu,sigma,delta=delta)
plot(dat)


#Skew t-distribution
dat <- rdemmix2(n,p,g,"mst",pro,mu,sigma,dof,delta)
plot(dat)

Results

R version 3.3.1 (2016-06-21) -- "Bug in Your Hair"
Copyright (C) 2016 The R Foundation for Statistical Computing
Platform: x86_64-pc-linux-gnu (64-bit)

R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.

R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.

Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.

> library(EMMIXskew)
Loading required package: lattice
Loading required package: mvtnorm
Loading required package: KernSmooth
KernSmooth 2.23 loaded
Copyright M. P. Wand 1997-2009
> png(filename="/home/ddbj/snapshot/RGM3/R_CC/result/EMMIXskew/rdemmix.Rd_%03d_medium.png", width=480, height=480)
> ### Name: rdemmix
> ### Title: Simulate Data Using Mixture Models
> ### Aliases: rdemmix rdemmix2 rdemmix3
> ### Keywords: cluster datasets
> 
> ### ** Examples
> 
> #specify the dimension of data, and number of clusters
> #the number of observations in each cluster
> n1=300;n2=300;n3=400;
> nn<-c(n1,n2,n3)
> 
> p=2
> g=3
> 
> 
> 
> #specify the distribution
> distr <- "mvn"
> 
> #specify mean and covariance matrix for each component
> 
> sigma<-array(0,c(2,2,3))
> for(h in 2:3) sigma[,,h]<-diag(2)
> sigma[,,1]<-cbind( c(1,-0.1),c(-0.1,1))
> mu  <- cbind(c(4,-4),c(3.5,4),c( 0, 0))
> 
> #reset the random seed 
> set.seed(111) 
> #generate the dataset
> dat <- rdemmix(nn,p,g,distr,    mu,sigma)
> 
> 
> 
> # alternatively one can use
> pro   <- c(0.3,0.3,0.4)
> n=1000
> set.seed(111)
> dat <- rdemmix2(n,p,g,distr,pro,mu,sigma)
> plot(dat)
> 
> # and 
> 
> set.seed(111)
> dobj <- rdemmix3(n,p,g,distr,pro,mu,sigma)
> plot(dobj$data)
> 
> 
> #other distributions such as "mvt","msn", and "mst".
> 
> #t-distributions
> 
> dof    <- c(3,5,5)
> dat <- rdemmix2(n,p,g,"mvt",pro,mu,sigma,dof)
> plot(dat)
> 
> #Skew Normal distribution
> delta <- cbind(c(3,3),c(1,5),c(-3,1))
> dat <- rdemmix2(n,p,g,"msn",pro,mu,sigma,delta=delta)
> plot(dat)
> 
> 
> #Skew t-distribution
> dat <- rdemmix2(n,p,g,"mst",pro,mu,sigma,dof,delta)
> plot(dat)
> 
> 
> 
> 
> 
> 
> 
> 
> dev.off()
null device 
          1 
>