dc_win: Dynamic Complexity
In FredHasselman/casnet: A Toolbox for Studying Complex Adaptive Systems and Networks

dc_win

R Documentation

Dynamic Complexity

Description

Calculates Dynamic Complexity, a complexity index for short and coarse grained time series.

Usage

dc_win(
  df,
  win = 0,
  scale_min,
  scale_max,
  doPlot = FALSE,
  doPlotF = FALSE,
  doPlotD = FALSE,
  returnFandD = FALSE,
  useVarNames = TRUE,
  colOrder = TRUE,
  useTimeVector = NA,
  timeStamp = "31-01-1999",
  markID = NA,
  markIDcolour = "grey",
  markIDlabel = "Time points of interest marked grey",
  markIDalpha = 0.5,
  NAdates = 1:(win - 1),
  trimFirstWin = TRUE
)

Arguments

`df`	A data frame containing multivariate time series data from 1 person. Rows should indicate time, columns should indicate the time series variables. All time series in `df` should be on the same scale, an error will be thrown if the range of the time series in`df` is not `⁠[scale_min,scale_max]⁠`.
`win`	Size of window in which to calculate Dynamic Complexity. If `win < NROW(df)` the window will move along the time series with a stepsize of `1` (default = `NROW(df)`)
`scale_min`	The theoretical minimum value of the scale. Used to calculate expected values, so it is important to set this to the correct value.
`scale_max`	The theoretical maximum value of the scale. Used to calculate expected values, so it is important to set this to the correct value.
`doPlot`	If `TRUE` shows a Complexity Resonance Diagram of the Dynamic Complexity and returns an invisible `ggplot2::ggplot()` object. (default = `FALSE`)
`doPlotF`	If `TRUE` shows a Complexity Resonance Diagram of the Fluctuation Intensity and returns an invisible `ggplot2::ggplot()` object. (default = `FALSE`)
`doPlotD`	If `TRUE` shows a Complexity Resonance Diagram of the Distribution Uniformity and returns an invisible `ggplot2::ggplot()` object. (default = `FALSE`)
`returnFandD`	Returns a list object containing the dynamic complexity series as well as the `F` and `D` series. (default = `FALSE`)
`useVarNames`	Use the column names of `df` as variable names in the Complexity Resonance Diagram (default = `TRUE`)
`colOrder`	If `TRUE`, the order of the columns in `df` determines the of variables on the y-axis. Use `FALSE` for alphabetic/numeric order. Use `NA` to sort by by mean value of Dynamic Complexity (default = `TRUE`)
`useTimeVector`	Parameter used for plotting. A vector of length `NROW(df)`, containing date/time information (default = `NA`)
`timeStamp`	If `useTimeVector` is not `NA`, a character string that can be passed to `lubridate::stamp()` to format the the dates/times passed in `useTimeVector` (default = `"01-01-1999"`)
`markID`	Numeric vector of integers in the range `⁠[length of window, length of timeseries]⁠`. Vertical lines will be drawn at these indices (default = `NA`)
`markIDcolour`	Colour of time point markers (default = `"red"`)
`markIDlabel`	Label added to subtitle explaining time point markers (default = `⁠Time points of interest marked red⁠`)
`markIDalpha`	Alpha of time point marker colour (default = `.5`)
`NAdates`	Should some dates be considered `NA`? Provide a numerical vector with indices, the default is to set `1:(win-1)` to NA. (default = `1:(win-1)`)
`trimFirstWin`	Display the first empty window (`1:win-1`)? (default = `TRUE`)
`plotMeanCD`	Plot the mean Dynamic Complexity at the top row of the resonance diagram? (default = `TRUE`)

Value

If doPlot = TRUE, a list object containing a data frame of Dynamic Complexity values and a ggplot2 object of the dynamic complexity resonance diagram. If doPlot = FALSE the data frame with Dynamic Complexity series is returned.

Author(s)

Merlijn Olthof

Fred Hasselman

References

Haken H, & Schiepek G. (2006). Synergetik in der Psychologie. Selbstorganisation verstehen und gestalten. Hogrefe, Göttingen.

Schiepek, G. (2003). A Dynamic Systems Approach to Clinical Case Formulation. European Journal of Psychological Assessment, 19, 175-184. https://doi.org/10.1027//1015-5759.19.3.175

Schiepek, G., & Strunk, G. (2010). The identification of critical fluctuations and phase transitions in short term and coarse-grained time series-a method for the real-time monitoring of human change processes. Biological cybernetics, 102(3), 197-207. https://doi.org/10.1007/s00422-009-0362-1

Examples


 # Dynamic Complexity analysis on part of the coloured noise dataset:
 data(ColouredNoise)
 # Make unit scale
 df <- data.frame(Brownianish = elascer(rowSums(ColouredNoise[,1:6])), pinkish = elascer(rowSums(ColouredNoise[,7:12])), whiteish = elascer(rowSums(ColouredNoise[,12:17])))
 dc_win(df = df, win = 56, scale_min = 0, scale_max = 1, doPlot = TRUE)

FredHasselman/casnet documentation built on May 5, 2024, 9:38 p.m.