wFGN.eval: Evaluation of the modified Whittle estimator for a...

In wonsang/wfGn: Estimation of the Hurst Parameter for Contaminated Fractional Gaussian Noises

Description

Statistical performance evaluation of the modified Whittle estimator of the Hurst parameter of a fractional Gaussian noise contaminated by additive outliers or noise.

Usage

wFGN.eval(H=NULL, n=1000, m=100, type="no", SNR=NULL, 
			ndeps=c(1e-7,1e-2), noise=TRUE, pertype="per", 
			minfun="qeta", weights=c(1,1,0), cluster=FALSE, 
			plot=TRUE, sav=FALSE)

Arguments

H	Hurst parameter. If H=NULL, H=0.1,0.2,...,0.9 are tested. Default is NULL.
n	sample size. Default is 1000.
m	the number of repetitions. Default is 100.
type	type of perturbation. Possible modes are "no","WN","AO". Refer to wFGN for details.
SNR	Signal to noise ratio.
ndeps	A vector of step sizes for optimization. Default is c(1e-7,1e-2).
noise	Enable the assumption of noise corruption. Default is TRUE.
pertype	type of periodogram. Possible modes are "per","taper".
minfun	type of minimization function. Possible modes are "qeta","lp","csum","combi".
weights	A vector of weights for each minimization function when minfun="combi".
cluster	A vector of machine names for parallel processing. For details, refer to the manual of package genoud.
plot	a boxplot of parameter estimation. Default is TRUE.
sav	Enable sample plots. Default is FALSE.

Details

The Hurst parameter of a fractional Gaussian noise is estimated by the modified Whittle estimator. This function evaluates the consistency of the Whittle estimator by several repetitions.

Value

Hdata	a m \times 1 or m \times 9 matrix of Hurst parameter estimates for fGn with different Hurst parameters
Hstat	a 4 \times 1 or 4 \times 9 matrix with a sample Hurst parameter, mean, standard deviation, and mean squared error (MSE) of Hurst parameter estimates
SNRdata	a m \times 1 or m \times 9 matrix of SNR estimates for fGn with different Hurst parameters
SNRstat	a 4 \times 1 or 4 \times 9 matrix with a sample SNR, mean, standard deviation, and mean squared error (MSE) of SNR estimates
Theta	a m \times 1 or m \times 9 matrix of scaling coefficient estimates

Author(s)

Wonsang You

References

Wonsang You (2010) Modified Whittle's Maximum Likelihood Estimator for Fractional Gaussian Noises Contaminated by Additive Noises, Technical Reports of the Leibniz Institute for Neurobiology, TR10015.

See Also

circFGN, perturbFGN, wFGN

Examples

dat <- wFGN.eval(H=0.2, n=10000, m=10, type="WN", SNR=-20, plot=TRUE)

wonsang/wfGn documentation built on May 14, 2019, 9:25 p.m.