Estimating Transfer Entropy via Copula Entropy

Jian Ma
10/10/2019
cs.LGcs.ITstat.ME

Official code: majianthu/transferentropy (43 stars, GPL-3.0, last commit 2023-04-07).

Abstract

Causal discovery is a fundamental problem in statistics and has wide applications in different fields. Transfer Entropy (TE) is a important notion defined for measuring causality, which is essentially conditional Mutual Information (MI). Copula Entropy (CE) is a theory on measurement of statistical independence and is equivalent to MI. In this paper, we prove that TE can be represented with only CE and then propose a non-parametric method for estimating TE via CE. The proposed method was applied to analyze the Beijing PM2.5 data in the experiments. Experimental results show that the proposed method can infer causality relationships from data effectively and hence help to understand the data better.

View on arXivView PDF

Code Implementations(1)

majianthu/transferentropyOfficial100%
GPL-3.0

Code for the paper "Estimating Transfer Entropy via Copula Entropy"

4313R, PythonNov 26, 20203 years agoGPL-3.0
causal-discoveryconditional-independencecopula-entropygranger-causalitytime-series-analysis+1 more

Similar Papers

Shapley-PC: Constraint-based Causal Structure Learning with a Shapley Inspired Framework

83% match1 repo22023

Conditional Independence Testing with Heteroskedastic Data and Applications to Causal Discovery

82% match2023

A Survey on Causal Discovery Methods for I.I.D. and Time Series Data

81% match2023

Causal Discovery via Conditional Independence Testing with Proxy Variables

81% match1 repo372023

Fast Nonparametric Conditional Independence Testing via Two-Stage Regression

81% match1 repo2026

Nonlinearity, Feedback and Uniform Consistency in Causal Structural Learning

81% match2023

Cite this paper

@article{ma2019estimating,
  title  = {Estimating Transfer Entropy via Copula Entropy},
  author = {Jian Ma},
  year   = {2019},
  eprint = {1910.04375},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1910.04375}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1910.04375.svg)](https://codeofpaper.com/paper/1910.04375)

Discussion