Performs a phase-randomization bootstrap estimate of the null hypothesis of independent time series
wmr.boot(w, smoothing = 1, reps = 1000, mr.func = "wmr")an object such as returned by mvcwt
degree of smoothing; larger values give greater smoothing
number of repetitions
a function taking a "mvcwt" object to be applied to each trial
an object of class "mvcwt" suitable for use with
contour.mvcwt.
The phases are randomized reps times for each combination of input
variable and scale. This package depends heavily on the dopar
function in the foreach package. If you do not have a lot of cores
available to you, you may need to let this run overnight.
Keitt, T. H. 2008. Coherent ecological dynamics induced by large-scale disturbance. Nature 454:331-4. doi:10.1038/nature06935.