| Title: | Complexity of Short and Coarse-Grained Time Series |
|---|---|
| Description: | While there are many well-established measures for identifying critical fluctuations and phase transitions, these measures only work with many points of measurement and thus are unreliable when studying short and coarse-grained time series. This package provides a measure for complexity in a time series that does not rely on long time series (Kaiser (2017), <doi:10.17605/OSF.IO/GWTKX>). |
| Authors: | Tim Kaiser |
| Maintainer: | Tim Kaiser <[email protected]> |
| License: | MIT + file LICENSE |
| Version: | 0.0.2-1 |
| Built: | 2024-12-05 06:59:15 UTC |
| Source: | CRAN |
A function to calculate the dynamic complexity of a series of observations, resulting from the degree of fluctuation and the degree of scattering. This measure is calculated in moving windows of a specified width, resulting in a series of values of a length equal to the length of the series of observations.
complexity(x, scaleMin, scaleMax, width = 7, measure = "complexity", rescale = FALSE)complexity(x, scaleMin, scaleMax, width = 7, measure = "complexity", rescale = FALSE)
x |
The data to be used (representing a series of observations). |
scaleMin |
Theoretical minimum of the data. Will default to the observed minimum of x. |
scaleMax |
Theoretical maximum of the data. Will default to the observed maximum of x. |
width |
Width of the moving window. Default is 7. |
measure |
Either "complexity", "fluctuation" or "distribution". Indicates which value should be returned. Default is "complexity". |
rescale |
If TRUE, rescales the returned values to scale minimum and maximum. This is sometimes useful for graphical interpretation or plotting. Default: FALSE. |
Tim Kaiser <[email protected]>
Kaiser, T. (2017). dyncomp: an R package for Estimating the Complexity of Short Time Series. DOI 10.17605/OSF.IO/GWTKX
t <- runif(100, 0, 10) c <- complexity(x = t, scaleMin = 0, scaleMax = 10, width = 5, measure = "complexity", rescale = TRUE) plot(t, type = "l") lines(c, col = "red", lty = 4)t <- runif(100, 0, 10) c <- complexity(x = t, scaleMin = 0, scaleMax = 10, width = 5, measure = "complexity", rescale = TRUE) plot(t, type = "l") lines(c, col = "red", lty = 4)