w - correlation

Share:

Description

Computes w - correlations (Golyandina, et.al. 2001) from a matrix containing reconstructed components in its columns.

Usage

1
w.cor(R, L)

Arguments

R

A matrix containing reconstructed components in its columns.

L

The window length, may be omitted in case of complete set of reconstructed components.

Details

W - correlation can be used to examine whether reconstructed components (RC) are independent (uncorrelated) or not. This is useful in signal to noise enhancement. RC being correlated to a high degree are assumed to correspond to the same signal.

Value

A suqare matrix containing the w - correlations.

Author(s)

Lukas Gudmundsson

References

Golyandina, N.; Nekrutkin, V. & Zhiglkilavskifi, A. Analysis of Time Series Structure: SSA and Related Techniques. CRC Press, 2001

See Also

decompSSA, decompSSAM

Examples

1
2
3
4
5
6
x <- sin(seq(0,10*pi,len=200))
x <- x + rnorm(x)/2
x.dc <- decompSSA(x,L=40)
x.rc <- reconSSA(x.dc,x,as.list(1:40))
x.wc <- w.cor(x.rc,40)
image(x.wc,col=gray(100:0/100))