知识卡片
预测检查应覆盖关键联合结构
比较模拟购买金额密度与经验密度可揭示结果边缘拟合问题,但边缘吻合不能保证处理、中介和结果的联合关系正确。因果目标依赖这些关系,应补充相应条件和联合诊断,并把拟合检查与识别论证分开。
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
posterior predictive check, and it helps us understand if the trained model is a good fit for the data. In the following code, we’ll do a posterior predictive check of In-Game Purchases; we’ll use the guide to generate samples and use those samples to repeatedly simulate In-Game Purchase datasets. For each simulated dataset, we’ll create a density curve. We’ll then plot these curves, along with
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:摘录中关于预测检查应覆盖关键联合结构的定义、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:posterior predictive check, and it helps us understand if the trained model is a good fit for the data. In the following code, we’ll do a posterior predictive check of In-Game Purchases; we’ll use the guide to generate samples and use those samples to repeatedly simulate In-Game Purchase datasets. For each simulated dataset, we’ll create a density curve. We’ll then plot these curves, along with