我在Github分享了拙作"Estimating transfer entropy via copula entropy"一文的代码，网址是：

https://github.com/majianthu/transferentropy/

代码使用多个条件独立性度量的R包（copent, cdcsis, CondIndTests, FOCI, GeneralisedCovarianceMeasure, KPC, ppcor, RCIT），在UCI的北京PM2.5数据上对比了如下条件独立性度量及R包：

• Transfer Entropy via Copula Entropy (TE) [1]; {copent}
• Conditional Distance Correlation (CDC) [2]; {cdcsis}
• Kernel-based Conditional Independence (KCI) [3]; {CondIndTests}
• COnditional DEpendence Coefficient (CODEC) [4]; {FOCI}
• Generalised Covariance Measure (GCM) [5]; {GeneralisedCovarianceMeasure}
• Kernel Partial Correlation (KPC) [6]; {KPC}
• Partial Correlation (pcor); {ppcor}
• Randomized conditional Correlation Test (RCoT) [7]. {RCIT}
  

• Ma, J. Estimating Transfer Entropy via Copula Entropy. arXiv preprint arXiv:1910.04375, 2019.
• Wang, X.; Pan, W.; Hu, W.; Tian, Y. & Zhang, H. Conditional distance correlation. Journal of the American Statistical Association, 2015, 110, 1726-1734.
• Zhang, K.; Peters, J.; Janzing, D. & Schölkopf, B. Kernel-based conditional independence test and application in causal discovery. Uncertainty in Artificial Intelligence, 2011, 804-813.
• Azadkia, M. & Chatterjee, S. A simple measure of conditional dependence. arXiv preprint arXiv:1910.12327, 2019.
• Shah, R. D. & Peters, J. The hardness of conditional independence testing and the generalised covariance measure. Annals of Statistics, 2020, 48, 1514-1538.
• Huang, Z.; Deb, N. & Sen, B. Kernel Partial Correlation Coefficient -- a Measure of Conditional Dependence. arXiv preprint arXiv:2012.14804, 2020.
• Strobl, E. V., Zhang, K., and Visweswaran, S. (2017). Approximate Kernel-based Conditional Independence Tests for Fast Non-Parametric Causal Discovery. http://arxiv.org/abs/1702.03877