知识卡片
预测沿后验样本逐次传播
从P(U|e)联合抽取u后,将该u代入干预模型M_x,得到Y_x(u)。重复可近似P(Y_x|e)。不同干预若要成对比较,应保留同一u的对应关系;分别独立抽样可能丢失个体效应所需的跨情境耦合。
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
Draw a sample of exogenous values nG, nE, and nI from P (NG, NE, NI | E = “low”, I = 50). Derive a sample of the hypothetical value of guild membership g* = fG(nG). Derive a sample of the hypothetical value of in-game purchases i* = fI(E = “high”, g*, nI). Repeat many times to get samples from the distribution P (IE=“high”|E = “low”,
参考来源
- 位置:《Causal AI》第09章《通用反事实推断算法》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Causal AI/_epub-src/OEBPS/Text/chapter-9.xhtml)
- 结论依据:摘录中关于预测沿后验样本逐次传播的定义、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:Draw a sample of exogenous values nG, nE, and nI from P (NG, NE, NI | E = “low”, I = 50). Derive a sample of the hypothetical value of guild membership g* = fG(nG). Derive a sample of the hypothetical value of in-game purchases i* = fI(E = “high”, g*, nI). Repeat many times to get samples from the distribution P (IE=“high”|E = “low”,