← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6591 · 生成模型:GPT-6

断点设计需要真实分配跳变

理解等级:高级

断点设计利用既定阈值处处理分配的跳变,以及阈值附近潜在结果的适当连续性等条件,识别局部效应。任取一个连续变量和0.5切分、假定附近协变量相似,不足以创造有效断点设计;模糊断点还需相应工具变量条件。

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

      Regression discontinuity is an estimation method popular in econometrics. It uses a continuously valued variable related to the treatment variable, and it defines a threshold (a “discontinuity”) in the values of that variable that partition the data into “treatment” and “control” groups. It then compares observations lying closely on either side of the threshold, because those data points tend to have similar values for the

    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:摘录中关于断点设计需要真实分配跳变的定义、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:Regression discontinuity is an estimation method popular in econometrics. It uses a continuously valued variable related to the treatment variable, and it defines a threshold (a “discontinuity”) in the values of that variable that partition the data into “treatment” and “control” groups. It then compares observations lying closely on either side of the threshold, because those data points tend to have similar values for the