wt.sig {biwavelet}

Determine significance of wavelet transform

Description

Determine significance of wavelet transform

Usage

wt.sig(
  d,
  dt,
  scale,
  sig.test = 0,
  sig.level = 0.95,
  dof = 2,
  lag1 = NULL,
  mother = "morlet",
  param = -1,
  sigma2 = NULL,
  arima.method = "CSS"
)

Arguments

d

Time series in matrix format (n rows x 2 columns). The first column should contain the time steps and the second column should contain the values.

dt

Length of a time step.

scale

The wavelet scale.

sig.test

Type of significance test. If set to 0, use a regular \chi^2 test. If set to 1, then perform a time-average test. If set to 2, then do a scale-average test.

sig.level

Significance level.

dof

Degrees of freedom for each point in wavelet power.

lag1

AR(1) coefficient of time series used to test for significant patterns.

mother

Type of mother wavelet function to use. Can be set to morlet, dog, or paul.

param

Nondimensional parameter specific to the wavelet function.

sigma2

Variance of time series

arima.method

Fitting method. This parameter is passed as the method Parameter to the arima function.

Value

Returns a list containing:

signif

vector containing significance level for each scale

signif

vector of red-noise spectrum for each period

Author(s)

Tarik C. Gouhier ([e-mail])

Code based on wavelet MATLAB program written by Christopher Torrence and Gibert P. Compo.

References

Torrence, C., and G. P. Compo. 1998. A Practical Guide to Wavelet Analysis. Bulletin of the American Meteorological Society 79:61-78.

Examples

# Not run: wt.sig(d, dt, scale, sig.test, sig.level, lag1,
#                 dof = -1, mother = "morlet", sigma2 = 1)