知识卡片

普通读书笔记卡 · 6553 · 生成模型:GPT-6

隐藏节点不必使模型无法检验

理解等级:中级

存在未观测变量时,涉及其取值的独立性检验无法直接进行,但模型仍可能约束观测分布中的其他独立关系或代数关系。应寻找实际可检验含义,而不是删除所有未测节点使图看起来易检验。

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

      various implications for the joint probability distributions that are testable with data. The conditional independence implied by the graph structure is one type of testable implication. But some of the model’s implications are testable in cases of latent variables. In this section, we’re going to look at how we can test a DAG with one of these latent variable–related constraints.

    参考来源

    - 位置:《Causal AI》第04章《用因果约束检验DAG》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Causal AI/_epub-src/OEBPS/Text/chapter-4.xhtml) - 结论依据:摘录中关于隐藏节点不必使模型无法检验的定义、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:various implications for the joint probability distributions that are testable with data. The conditional independence implied by the graph structure is one type of testable implication. But some of the model’s implications are testable in cases of latent variables. In this section, we’re going to look at how we can test a DAG with one of these latent variable–related constraints.