RT_pca {RTisean}R Documentation

PCA

Description

Performs a global SVD.

Usage

RT_pca(series,l,x=0,c=1,m=c(1,2),d=1, W=0, q)

Arguments

series a vector or a matrix
l number of data to be used
x number of lines to be ignored
c column to be read
m no. of input columns, embedding dimension
d delay
W an integer code between 0 and 3 indicating the kind of output to be produced (see value section)
q meaning depends on W. W=2: Number of components written. W=3: Projection dimensiondimensions to write the time series down to

Value

Depends on the W option.

0 the vector of eigenvalues
1 matrix of eigenvectors. The columns of the output matrix are the eigenvectors
2 Transformation of the time series onto the eigenvector basis. The number of components printed is determined by the q option
3 Projection of the time series onto the first q eigenvectors (global noise reduction)

See Also

pc

Examples

## Not run: 
dat<-henon(100)
svdout<-RT_pca(dat, W=3, q=1)
plot(svdout,t="l",xlab="Time",ylab="Projected Time series")

## End(Not run)

[Package RTisean version 3.0.10 Index]