← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6543.a · 生成模型:GPT-6

缺边同样承载强假设

理解等级:中级

绘制A→E→O而不画A→O,意味着在所选变量层次上排除了A对O的直接作用;这可能带来可检验的独立性约束。建图时应同时讨论为什么连边和为什么不连边,而不只为已有箭头提供故事。

这张卡片看不懂?

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

      The assumptions encoded in a causal DAG are strong. Let’s look again at the transportation DAG from figure 3.2, shown again in figure 3.5. Consider the alternatives to that DAG; how many possible DAGs could we draw on this simple six-node system? The answer is 3,781,503, so when we use a causal DAG to communicate our assumptions about this system, we’re communicating our top choice

    参考来源

    - 位置:《Causal AI》第03章《构建因果图模型》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Causal AI/_epub-src/OEBPS/Text/chapter-3.xhtml) - 结论依据:摘录中关于缺边同样承载强假设的定义、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:The assumptions encoded in a causal DAG are strong. Let’s look again at the transportation DAG from figure 3.2, shown again in figure 3.5. Consider the alternatives to that DAG; how many possible DAGs could we draw on this simple six-node system? The answer is 3,781,503, so when we use a causal DAG to communicate our assumptions about this system, we’re communicating our top choice