知识卡片
局部图不确定未必影响目标
若两种候选图下同一调整集都阻断目标的所有后门路径,则某条边方向的不确定未必影响该目标的调整识别。这个结论仅针对检查过的候选图和查询,不能扩展成图上其他错误都无关紧要。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
已有反馈 · 0 条
还没有人提交反馈。
在整书笔记中的位置
原书出处 · 1 处
- · 查看原书依据
For example, the key assumption behind the backdoor adjustment estimand is that we can adjust for all sources of confounding from common causes. In our original DAG, we have an edge from Time Spent Playing to Player Skill Level. What if you weren’t sure about the direction of this edge, as illustrated in figure 11.6.
参考来源
- 位置:《Causal AI》第11章《构建因果推断工作流》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Causal AI/_epub-src/OEBPS/Text/chapter-11.xhtml)
- 结论依据:摘录中关于局部图不确定未必影响目标的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。
- 原始内容:For example, the key assumption behind the backdoor adjustment estimand is that we can adjust for all sources of confounding from common causes. In our original DAG, we have an edge from Time Spent Playing to Player Skill Level. What if you weren’t sure about the direction of this edge, as illustrated in figure 11.6.