Entropy Based Analysis and Tests for Time Series

Implements an Entropy measure of dependence based on the Bhattacharya-Hellinger-Matusita distance. Can be used as a (nonlinear) autocorrelation/crosscorrelation function for continuous and categorical time series. The package includes tests for serial and cross dependence and nonlinearity based on it. Some routines have a parallel version that can be used in a multicore/cluster environment. The package makes use of S4 classes.

tseriesEntropy

The R package tseriesEntropy implements an entropy measure of dependence based on the Bhattacharya-Hellinger-Matusita distance. It can be used as a (nonlinear) autocorrelation/crosscorrelation function for continuous and categorical time series. The package includes tests for serial and cross dependence and nonlinearity based on it. Some routines have a parallel version that can be used in a multicore/cluster environment. The package makes use of S4 classes.

Authors

• Simone Giannerini, University of Bologna

References

Giannerini S., Maasoumi E., Bee Dagum E., (2015), Entropy testing for nonlinear serial dependence in time series, Biometrika, 102(3), 661–675.

Giannerini S, Goracci G. (2023) Entropy-Based Tests for Complex Dependence in Economic and Financial Time Series with the R Package tseriesEntropy, Mathematics, 11(3):757.

Granger C. W. J., Maasoumi E., Racine J., (2004) A dependence metric for possibly nonlinear processes. Journal of Time Series Analysis, 25(5), 649–669.

Installation

You can install the stable version on CRAN:

install.packages('tseriesEntropy')

You can install the development version of tseriesEntropy from GitHub with:

# install.packages("devtools")
devtools::install_github("sgiannerini/tseriesEntropy")

License

This package is free and open source software, licensed under GPL.