stat_op

docblock

stat_op(data; chart_choice, m=3, d=1, add_noise=false)
stat_op(data, lam; chart_choice, m=3, d=1, add_noise=false)

Compute the ordinal-pattern chart statistic for the time series data. The ordinal patterns are indexed via the Lehmer code (see perm_to_lehm_idx!).

The first method computes the statistic once for the whole series and returns the vector [stat, p_rel], where stat is the chart statistic and p_rel the vector of relative ordinal-pattern frequencies.

The second method additionally applies EWMA smoothing with parameter lam (Equation (5) in Weiß and Testik (2023)) and returns the tuple (stats_all, p_rel), where stats_all contains the sequentially computed EWMA chart statistics.

data: time series (vector).
lam::Float64: smoothing parameter of the EWMA statistic.
chart_choice: one of Shannon(), ShannonExtropy(), DistanceToWhiteNoise(), UpDownBalance(), Persistence(), RotationalAsymmetry(), UpDownScaling(). For Shannon and ShannonExtropy, the statistic is in the logarithm base of the chart, which must be larger than 1. Both default to base 2 in ComplexityMeasures.jl; use Shannon(base=exp(1)) for the natural logarithm used in the papers.
m::Int=3: length of the ordinal patterns.
d::Int=1: delay between observations of a pattern.
add_noise::Bool=false: add uniform noise to data to break ties (recommended for discrete-valued series).