timsac (version 1.3.0)

fftcor: Auto And/Or Cross Correlations via FFT

Description

Compute auto and/or cross covariances and correlations via FFT.

Usage

fftcor(y, lag=NULL, isw=4, plot=TRUE, lag_axis=TRUE)

Arguments

y

data of channel X and Y (data of channel Y is given for isw = 2 or 4 only).

lag

maximum lag. Default is $2 \sqrt{n}$, where $n$ is the length of the time series y.

isw

numerical flag giving the type of computation. rl{ 1 : auto-correlation of X (one-channel) 2 : auto-correlations of X and Y (two-channel) 4 : auto- and cross- correlations of X and Y (two-channel) }

plot

logical. If TRUE (default) cross-correlations are plotted.

lag_axis

logical. If TRUE (default) with plot=TRUE, $x$-axis is drawn.

Value

• acov
  auto-covariance.
• ccov12
  cross-covariance.
• ccov21
  cross-covariance.
• acor
  auto-correlation.
• ccor12
  cross-correlation.
• ccor21
  cross-correlation.
• mean
  mean.

References

H.Akaike and T.Nakagawa (1988) Statistical Analysis and Control of Dynamic Systems. Kluwer Academic publishers.

Examples

# Example 1
  x <- rnorm(200)
  y <- rnorm(200)
  xy <- array(c(x,y), dim=c(200,2))
  fftcor(xy, lag_axis=FALSE)

  # Example 2
  xorg <- rnorm(1003)
  x <- matrix(0,1000,2)
  x[,1] <- xorg[1:1000]
  x[,2] <- xorg[4:1003]+0.5*rnorm(1000)
  fftcor(x, lag=20)