miData: Empirical Estimation of the Entropy from a Table of Counts

In abn: Modelling Multivariate Data with Additive Bayesian Networks

Empirical Estimation of the Entropy from a Table of Counts

Description

This function empirically estimates the Mutual Information from a table of counts using the observed frequencies.

Usage

miData(freqs.table, method = c("mi.raw", "mi.raw.pc"))

Arguments

freqs.table	a table of counts.
method	a character determining if the Mutual Information should be normalized.

Details

The mutual information estimation is computed from the observed frequencies through a plugin estimator based on entropy.

The plugin estimator is

I(X, Y) = H (X) + H(Y) - H(X, Y)

, where

H()

is the entropy computed with entropyData.

Value

Mutual information estimate.

References

Cover, Thomas M, and Joy A Thomas. (2012). "Elements of Information Theory". John Wiley & Sons.

See Also

discretization

Examples

## Generate random variable
Y <- rnorm(n = 100, mean = 0, sd = 2)
X <- rnorm(n = 100, mean = 5, sd = 2)

dist <- list(Y="gaussian", X="gaussian")

miData(discretization(data.df = cbind(X,Y), data.dists = dist,
                      discretization.method = "fd", nb.states = FALSE),
                      method = "mi.raw")

abn documentation built on Nov. 3, 2023, 5:08 p.m.