plot.seedCCA: Plotting class "seedCCA" depending on the value of 'type'

In seedCCA: Seeded Canonical Correlation Analysis

Plotting class "seedCCA" depending on the value of type

Description

The function is for plotting class "seedCCA". Depending on subclass defined by the value of type, its resulting plot is different.

Usage

## S3 method for class 'seedCCA'
plot(x, ref=90, eps=0.01, ...)

Arguments

x	The name of an object of class "seedCCA"
ref	numeric, the value for reference line. It must be chosen between 0 and 100. It works only for subclass "finalCCA".
eps	numeric, a value to terminate projections. It must be chosen between 0 and 1. The default is equal to 0.01. It works only for subclass "seedpls".
...	arguments passed to the plot.method

Details

subclass "finalCCA": the function makes a plot for percents of cumulative canonical correlations.

subclass "seedpls": the function returns a proper number of projections and plot of the projection increment against the number of projections. A proper number of projections is indicated with a blue-color vertical bar in the plot. Only for subclass "seedpls", the output is retured. See Value part.

subclass "seedols": No plotting

subclass "selectu": the function makes a plot for increment of iterative projections by the output of subclass "selectu".

Value

proper.u	proper value of the number of projections
nFu	incrments (n*Fu) of the iterative projection.
u	the maximum number of projections from "seedpls" object
eps	a value for terminating the projection. The default value is equal to 0.01.

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])

fit.cca <- seedCCA(X[,1:4],Y[,1:4],type="cca")
fit.seed1 <- seedCCA(X,Y, type="seed1")
fit.pls1 <- seedCCA(X,Y[,1],type="pls")
fit.selu <- selectu(X,Y, type="seed2")

plot(fit.cca)
plot(fit.seed1, ref=95)
plot(fit.pls1)
plot(fit.pls1, eps=0.00001)
plot(fit.selu)

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