FitFGN: MLE estimation for FGN

In FGN: Fractional Gaussian Noise and power law decay time series model fitting

Description

Exact MLE estimation for FGN

Usage

FitFGN(z, demean = TRUE, MeanMLEQ = FALSE, lag.max = "default")

Arguments

z	time series, vector or ts object.
demean	if True, subtract mean. Otherwise assume it is zero.
MeanMLEQ	if True, an iterative algorithm is used for exact simultaneous MLE estimation of the mean and other parameters.
lag.max	the residual autocorrelations are tabulated for lags 1, ..., lag.max. Also lag.max is used for the Ljung-Box portmanteau test.

Details

The exact loglikelihood function is maximized numerically using optimize. The standard error for the H parameter is estimated (McLeod, Yu and Krougly, 2007).

Value

A list with class name "FitAR" and components:

loglikelihood	value of the loglikelihood
H	estimate of H parameter
SEH	SE of H estimate
sigsqHat	innovation variance estimate
muHat	estimate of the mean
SEmu	SE of mean
Rsq	R-squared, coefficient of forecastability
LjungBox	table of Ljung-Box portmanteau test statistics
res	normalized residuals, same length as z
demean	TRUE if mean estimated otherwise assumed zero
IterationCount	number of iterations in mean mle estimation
MLEMeanQ	TRUE if mle for mean algorithm used
tsp	tsp(z)
call	result from match.call() showing how the function was called
DataTitle	returns attr(z,"title")

Author(s)

A.I. McLeod

References

McLeod, A.I., Yu, Hao, Krougly, Zinovi L. (2007). Algorithms for Linear Time Series Analysis, Journal of Statistical Software.

See Also

GetFitFGN, FitRegressionFGN, Boot.FitFGN, coef.FitFGN, plot.FitFGN, print.FitFGN, summary.FitFGN, HurstK

Examples

data(NileMin)
out<-FitFGN(NileMin)
summary(out)
plot(out)
coef(out)

FGN documentation built on May 30, 2017, 7:19 a.m.