Calculates the autocovariance sequence for an input time series.
Usage
ACVS(x, biased=TRUE, center=TRUE)
Arguments
x
a numeric vector representing a uniformly sampled real-valued time series.
biased
a logical value. If TRUE, the biased estimator (normalized by \(N\), the number of samples in the time series) is returned.
If FALSE, the result is the unbiased estimator (the kth ACVS value is normalized by \(N - |k|\) for
the unbiased case where \(k=0,\ldots,N-1\)). Default: TRUE.
center
a logical value. If TRUE, the series is first centered (sample mean is subtracted
from series) prior to calculating the ACVS. Default: TRUE.
Value
a numeric vector containing the single-sided ACVS for lags \(k=0,\ldots,N-1\) where \(N\) is the length
of the input time series.
# NOT RUN {## calculate the ACVS for an N(0,1) realization plot(seq(0,99), ACVS(rnorm(100)), type="l", lwd=2,
xlab="lag",ylab="ACVS(rnorm(100))")
ifultools::gridOverlay()
# }