This package implements various estimators of the Shannon entropy. Most estimators in this package can be applied in ``small n, large p'' situations, i.e. when there are many more bins than counts.
The main function of this package is entropy
, which provides
a unified interface to various entropy estimators. Other functions included in this package are
estimators of Kullback-Leibler divergence (KL.plugin
), mutual information (mi.plugin
) and of the chi-squared divergence (chi2.plugin
).
Furthermore, there are functions to compute the G statistic (Gstat
)
and the chi-squared statistic (chi2stat
).
If you use this package please cite: Jean Hausser and Korbinian Strimmer. 2009. Entropy inference and the James-Stein estimator, with application to nonlinear gene association networks. J. Mach. Learn. Res. 10: 1469-1484. Available online from https://jmlr.csail.mit.edu/papers/v10/hausser09a.html.
This paper contains a detailed statistical comparison of the estimators available
in this package. It also describes the shrinkage entropy estimator entropy.shrink
.
See website: https://strimmerlab.github.io/software/entropy/