relative_entropy: Relative Entropy

In rinform: An R Wrapper of the 'Inform' C Library for Information Analysis of Complex Systems

Description

Compute the average or local relative entropy between two time series treating each as observations from a distribution.

Usage

relative_entropy(xs, ys, local = FALSE)

Arguments

xs	Vector or matrix specifying one or more time series.
ys	Vector or matrix specifying one or more time series.
local	Boolean specifying whether to compute the local relative entropy.

Value

Numeric giving the average relative entropy or a vector giving the local relative entropy.

Examples

xs <- c(0, 1, 0, 0, 0, 0, 0, 0, 0, 1)
ys <- c(0, 1, 1, 1, 1, 0, 0, 1, 0, 0)
relative_entropy(xs, ys)       # 0.2780719
relative_entropy(ys, xs)       # 0.3219281

# [1]  0.6780719 -1.3219281
relative_entropy(xs, ys, local = TRUE)

xs <- c(0, 0, 0, 0)
ys <- c(0, 1, 1, 0)
relative_entropy(xs, ys)       # 1.0
relative_entropy(ys, xs)       # NaN

rinform documentation built on April 1, 2018, 12:12 p.m.