Given a set of indices which represent the whitest transform available in a DWPT, this function randomizes the coefficients in each of the crystals comprising the transform (via random selection with replacement) followed by an inverse transform. The z is a bootstrapped version of the original time series.
1 2  wavBootstrap(x, white.indices=wavDWPTWhitest(x),
n.realization=1, wavelet="s8", n.level=NULL)

x 
a vector containing a uniformlysampled realvalued time series or an
object of class 
n.level 
the number of decomposition levels. This argument is used only if

n.realization 
the number of realizations to generate. Default: 
wavelet 
a character string denoting the filter type.
See 
white.indices 
a 
a list of numeric vectors containing the bootstrapped series. If n.realization=1
,
the the output is a numeric vector (not packed into a list
).
D. B. Percival, S. Sardy and A. C. Davison, Wavestrapping Time Series: Adaptive WaveletBased Bootstrapping, in W. J. Fitzgerald, R. L. Smith, A. T. Walden and P. C. Young (Eds.), Nonlinear and Nonstationary Signal Processing, Cambridge, England: Cambridge University Press, 2001.
wavDWPT
, wavDWPTWhitest
.
1 2 3 4 5 6 7 8 9  ## wavestrap the sunspots series
x < as.numeric(sunspots)
z < wavBootstrap(x, n.realization=1)
ifultools::stackPlot(x=seq(along=sunspots),
y=data.frame(x, z, abs(z)),
ylab=list(text=c("sunspots","wavestrap","wavestrap")))
title("Waveletbased bootstrapping of sunspots series", cex=0.7)

Questions? Problems? Suggestions? Tweet to @rdrrHQ or email at ian@mutexlabs.com.
All documentation is copyright its authors; we didn't write any of that.