criticalvaluesWSP {sowas}R Documentation

Estimates critical values for Wavelet spectra

Description

This function estimates critical values for the Wavelet spectra by means of Monte Carlo simulations. Null Hypothesis is an AR1 (red noise) process fitted to the given time series.

Usage

criticalvaluesWSP(ts, s0 = 1, noctave = 5, nvoice = 10, w0 = 2*pi, swabs
= 0, tw = 0, siglevel = 0.95, nreal = 1000)

Arguments

ts time series object
s0 lowest calculated scale in units of the time series
noctave number of octaves
nvoice number of voices per octave
w0 time/frequency resolution omega0
swabs length of smoothing window is 2swabs+1
tw length of smoothing window in time direction is 2*s*tw+1
siglevel significance level, e.g. 0.9, 0.95 or 0.99. siglevel might also be a vector, e.g. c(0.9,0.95) to plot more contourlines.
nreal number of realizations to estimate critical values for the corresponding significance values, default 1000

Details

nreal might be chosen as 100 for a rough estimate of significance. However, it is for sure not suitable to reliably distinguish between 95 and 99 percent significance values. In this case, at least nreal=1000 should be chosen.

Value

Returns a matrix of scale DEPENDENT critical values. The number of rows of the matrix corresponds to the number of chosen significance values. The number of columns equals the number of scales.

Note

Author(s)

D. Maraun

References

D. Maraun and J. Kurths, Nonlin. Proc. Geophys. 11: 505-514, 2004

See Also

wsp

Examples

##
[Package sowas version 0.93 Index]