Performs signal extraction and optimal filtering as discussed in Chapter 4.
SigExtract(series, L = c(3, 3), M = 50, max.freq = 0.05)univariate time series to be filtered
degree of smoothing (may be a vector); see spans in spec.pgram
for more details
number of terms used in the lagged regression approximation
truncation frequency, which must be larger than 1/M.
Returns plots of (1) the original and filtered series, (2) the estiamted spectra of each series, (3) the filter coefficients and the desired and attained frequency response function. The filtered series is returned invisibly.
The basic function of the script, and the default setting, is to remove frequencies above 1/20 (and, in particular, the seasonal frequency of 1 cycle every 12 time points). The sampling frequency of the time series is set to unity prior to the analysis.