知识卡片
部分识别报告兼容值集合
部分识别给出所有兼容指定分布和假设的模型允许的目标范围。这个结构范围不同于估计误差形成的置信区间,也不同于先验下的可信区间;有限数据时可能还需对界限端点的不确定性另作报告。
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
- · 识别与因果层级
原书出处 · 1 处
- · 查看原书依据
the size of your data increases. (Successful convergence assumes typical “regularity” conditions for Bayesian estimation. Results will depend on the quality of the prior.) But even if it doesn’t converge to the true value, your assumptions might still enable convergence to a ballpark region around the true value that is small enough to be useful (this is called partial identification, as described in section 10.9).
参考来源
- 位置:《Causal AI》第10章《识别与因果层级》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Causal AI/_epub-src/OEBPS/Text/chapter-10.xhtml)
- 结论依据:摘录中关于部分识别报告兼容值集合的定义、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 size of your data increases. (Successful convergence assumes typical “regularity” conditions for Bayesian estimation. Results will depend on the quality of the prior.) But even if it doesn’t converge to the true value, your assumptions might still enable convergence to a ballpark region around the true value that is small enough to be useful (this is called partial identification, as described in section 10.9).