iniCCA: Initialized CCA in seeded CCA

In seedCCA: Seeded Canonical Correlation Analysis

Initialized CCA in seeded CCA

Description

Returns the canonical coefficient matrices from the initialized step in seeded CCA. The initialzied CCA is done only for the first set in its first argument. The num.d must be less than or equal to the dimension of the second set.

Usage

iniCCA(X, Y, u, num.d)

Arguments

X	numeric matrix (n * p), the first set of variables: this set of variables alone is reduced.
Y	numeric matrix (n * r), the second set of variables
u	numeric, the terminiating index of the projection
num.d	numeric, the first "num.d" eigenvectors of cov(X,Y) to replace cov(X,Y), if min(p,r) relatively bigger than n. The num.d must be less than or equal to min(p,r).

Value

B	the initialized CCAed coefficient matrix projected by the value of u

Examples

########  data(cookie) ########
data(cookie)
myseq<-seq(141,651,by=2)
X<-as.matrix(cookie[-c(23,61),myseq])
Y<-as.matrix(cookie[-c(23,61),701:704])
min.pr <- min( dim(X)[2], dim(Y)[2])
MX0 <- iniCCA(X, Y, u=4, num.d=min.pr)
ini.X <- X%*%MX0

########  data(nutrimouse) ########
data(nutrimouse)
Y<-as.matrix(nutrimouse$lipid)
X<-as.matrix(nutrimouse$gene)
MX0 <- iniCCA(X, Y, u=4, num.d=4)
MY0 <- iniCCA(Y, X, u=5, num.d=4)
ini.X <- X %*% MX0
ini.Y <- Y %*% MY0

seedCCA documentation built on June 9, 2022, 9:05 a.m.