dprcomp: Compute DPCA filter coefficients

In freqdom: Frequency Domain Analysis for Multivariate Time Series

Description

For a given process X eigendecompose it's spectral density and use an inverse fourier transform to get coefficients of the optimal filter. For details please refer to Hormann et al paper.

Usage

dprcomp(X, V = NULL, lags = -10:10, q = NULL, weights = NULL,
  freq = NULL)

Arguments

X	multivariate stationary time series
V	correlation structure between coefficients of vectors (default diagonal)
lags	requested filter coefficients
q	window for spectral density estimation as in spectral.density
weights	as in spectral.density
freq	frequency grid to estimate on as in spectral.density

Value

principal components series

References

Siegfried Hormann, Lukasz Kidzinski and Marc Hallin Dynamic Functional Principal Component Research report, 2012

See Also

dpca.inverse, dpca.scores

freqdom documentation built on May 2, 2019, 5:55 p.m.