optimise_dim_FNN: Finds the minimal embedding dimension of a series 'v'...
In kahaaga/tstools: Useful functions

Description Usage Arguments Details Value

From: M. B. Kennel, R. Brown, and H. D. I. Abarbanel, Determining embedding dimension for phase-space reconstruction using a geometrical construction, Phys. Rev. A 45, 3403 (1992).

optimise_dim_FNN(v, max.embedding.dim = 10, embedding.lag = 1,
  orbital.lag = NULL, lag.max = ceiling(length(v) * 0.2),
  lag.method = "correlation", plot.temporal.correlation.function = F,
  threshold = 0.95)

`v`	A numeric vector containing the series.
`max.embedding.dim`	The maximum embedding dimension to consider
`embedding.lag`	The embedding lag.
`orbital.lag`	The Theiler window. An orbital lag to avoid temporal correlation. Defaults to NULL, in which case the orbital lag is chosen as the first local minima of the autocorrelation function (lag.method = "acf" or lag.method = "autocorrelationfunction") or the lagged mutual information function (lag.method = "mi" or lag.method = "mutual information").
`lag.max`	The maximum number of lags for the autocorrelation function (lag.method = "acf" or lag.method = "autocorrelation function") or the mutual information function (lag.method = "mi" or lag.method = "mutual information function").
`lag.method`	The method to compute the orbital lag (Theiler window), which excludes temporal neighbours to reduce correlation bias. Either use the autocorrelation function (lag.method = "acf") or the lagged mutual information function (lag.method = "mi")
`plot.temporal.correlation.function`	Should the function used to determine the orbital lag (temporal separation window) be plotted?
`threshold`	The fraction of real nearest neighbours to pass the test.

Implemented in the TISEAN package by Reiner Hegger, Holger Kantz and Thomas Schreiber, and ported to R in the tseriesChaos package by Antonio Fabio Di Narzo

The minimum embedding dimension yielding zero false neighbours or a false neighbours proportion below some threshold.

kahaaga/tstools documentation built on May 24, 2019, 5:01 a.m.