fractal (version 2.0-4)

dispersion: Dispersion analysis

Description

Dispersion analysis measures the standard deviation of aggregated means of a time series taken over logarithmically distributed scales. Dispersion analysis is designed for the analysis of fractional Gaussian noise and should not be used for analyzing fractional Brownian motion.

Usage

dispersion(x, front=FALSE)

Arguments

x

a numeric vector or signalSeries object containing a uniformly sampled real-valued time series.

front

a logical value. If TRUE, the aggregation is started from the beginning of the time series so that the first points will be included in the result. Otherwise, the aggregation is shifted to include the end of the series. Default: FALSE.

Value

a list containing the scale and dispersion analysis statistic vectors.

References

Bassingthwaighte, J. B., and G. M. Raymond. Evaluation of the dispersional analysis method for fractal time series, Annals Biomedical Engineering, 23, 491--505, 1995.

See Also

DFA, RoverS.

Examples

# NOT RUN {
set.seed(100)
z <- dispersion(rnorm(1024))
plot(log(z$scale),log(z$sd))
# }