Causality measures and analysis: A rough set framework
作者：
Highlights：
• Causality between attributes can be measured by rough set theory.
• Interventions can be handled by lower approximation and statistical independence.
• Counterfactual interpretation is given for the complete attribute-value table.
• The degree of dependency becoming zero, causation between attributes might exist.
• Lower approximations being empty implies the joint probabilities are great than 0.
摘要
•Causality between attributes can be measured by rough set theory.•Interventions can be handled by lower approximation and statistical independence.•Counterfactual interpretation is given for the complete attribute-value table.•The degree of dependency becoming zero, causation between attributes might exist.•Lower approximations being empty implies the joint probabilities are great than 0.
论文关键词：Rough set,Lower approximation,Causal effect,Intervention,Counterfactual
论文评审过程：Received 21 August 2018, Revised 1 June 2019, Accepted 2 June 2019, Available online 3 June 2019, Version of Record 25 June 2019.
论文官网地址：https://doi.org/10.1016/j.eswa.2019.06.004
