Computes the quadrature mirror filter of a series of even length.
Usage
wt.filter.qmf(x, inverse=FALSE)
Arguments
x
A numeric vector of even length
inverse
A logical flag indicating whether to compute the
inverse quadrature mirror filter.
Value
A numeric vector which contains the values of x in reverse
order, with the values of the resulting vector at even indices being
negated in the case that inverse=FALSE and the values at odd
indices being negated in the case that inverse=TRUE.
Details
The quadrature mirror filter is computed as outlined in
Percival and Walden, page 75. Specifically, the forward QMF makes use
of a wavelet filter to obtain a scaling filter and the inverse QMF
does the opposite.
References
Percival, D. B. and A. T. Walden (2000) Wavelet Methods
for Time Series Analysis, Cambridge University Press.
# NOT RUN {# obtain both the la8 wavelet and scaling filtersla8 <- wt.filter("la8")
# now compare output of qmf with values in wt.filter objectwt.filter.qmf(la8@h)
la8@g
# }