spp.mle: Wavelet-based Maximum Likelihood Estimation for Seasonal...

In waveslim: Basic Wavelet Routines for One-, Two-, and Three-Dimensional Signal Processing

Wavelet-based Maximum Likelihood Estimation for Seasonal Persistent Processes

Description

Parameter estimation for a seasonal persistent (seasonal long-memory) process is performed via maximum likelihood on the wavelet coefficients.

Usage

spp.mle(y, wf, J = log(length(y), 2) - 1, p = 0.01, frac = 1)

spp2.mle(y, wf, J = log(length(y), 2) - 1, p = 0.01, dyadic = TRUE, frac = 1)

Arguments

y	Not necessarily dyadic length time series.
wf	Name of the wavelet filter to use in the decomposition. See wave.filter for those wavelet filters available.
J	Depth of the discrete wavelet packet transform.
p	Level of significance for the white noise testing procedure.
frac	Fraction of the time series that should be used in constructing the likelihood function.
dyadic	Logical parameter indicating whether or not the original time series is dyadic in length.

Details

The variance-covariance matrix of the original time series is approximated by its wavelet-based equivalent. A Whittle-type likelihood is then constructed where the sums of squared wavelet coefficients are compared to bandpass filtered version of the true spectral density function. Minimization occurs for the fractional difference parameter d and the Gegenbauer frequency f_G, while the innovations variance is subsequently estimated.

Value

List containing the maximum likelihood estimates (MLEs) of \delta, f_G and \sigma^2, along with the value of the likelihood for those estimates.

Author(s)

B. Whitcher

References

Whitcher, B. (2004) Wavelet-based estimation for seasonal long-memory processes, Technometrics, 46, No. 2, 225-238.

See Also

fdp.mle

waveslim documentation built on June 22, 2024, 9:43 a.m.