Identifiability of causal effect for a simple causal model  

作　　者：郑忠国 童行伟 张艳艳 

出　　处：《Science China Mathematics》2002年第3期335-341,共7页中国科学：数学（英文版）

基　　金：This work was supported by the National Natural Science Foundation of China (Grant Nos. 39930160, 19871003).

摘　　要：Counterfactual model is put forward to discuss the causal inference in the directed acyclic graph and its corresponding identifiability is thus studied with the ancillary information based on conditional independence. It is shown that the assumption of ignorability can be expanded to the assumption of replaceability, under which the causal effects are identifiable.Counterfactual model is put forward to discuss the causal inference in the directed acyclic graph and its corresponding identifiability is thus studied with the ancillary information based on conditional independence. It is shown that the assumption of ignorability can be expanded to the assumption of replaceability,under which the causal efiects are identifiable.

关 键 词：directed ACYCLIC graph  intervention  CAUSAL effects  ancillary information  ignorability replaceability. 

分 类 号：O212[理学—概率论与数理统计]