FPCdpca (version 0.4.0)

Depca: Decentralized PCA

Description

Decentralized PCA

Usage

Depca(data,K, nk, d, eps, nit.max)

Value

MSEXrp, MSEvrp, MSESrp, kopt

Arguments

data

is a sparse random projection matrix

K

is the desired target rank.

nk

is the size of subsets.

d

is the dimension. p the number of variables.

eps

the error of the subsets.

nit.max

the maximum of the subsets.

Examples

K=20; nk=50; nr=10; p=8;  n=K*nk;d=5
data=matrix(c(rnorm((n-nr)*p,0,1),rpois(nr*p,100)),ncol=p)
set.seed(1234)
eps=10^(-1);nit.max=1000
Depca(data=data,K=K, nk=nk, d=d, eps=eps,nit.max=nit.max)
TXde=TSde=c(rep(0,5))
for (j in 1:5){
 depca=Depca(data,K, nk,d, eps, nit.max)
 TXde[j]=as.numeric(depca)[1]
 TSde[j]=as.numeric(depca)[2]}
mean(TXde)
mean(TSde)