← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 9245.a · 生成模型:GPT-6

误差方差估计需扣除拟合自由度

理解等级:中级

含截距和k个独立预测列的满秩OLS,在相应同方差模型下用SSE/(n−k−1)估计误差方差。原6.6首式写n−(k−1)有误,后文n−(k+1)及30−4例一致。

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

      In the above equation, is the sum of the square of errors also known as SSE, n is the number of observations (n = 30 for our example), k is the number of independent variables (k = 3 for our example). The value of SSE is reported in the Analysis of Variance part of Table 14.2. From this table, SSE = 36,207.

    参考来源

    - 位置:《Machine Learning Fundamentals: Concepts, Models, and Applications》第06章《监督学习模型》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Machine Learning Fundamentals: Concepts, Models, and Applications/_epub-src/OEBPS/xhtml/19_chapter06.xhtml) - 结论依据:摘录中关于误差方差估计需扣除拟合自由度的定义、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:In the above equation, is the sum of the square of errors also known as SSE, n is the number of observations (n = 30 for our example), k is the number of independent variables (k = 3 for our example). The value of SSE is reported in the Analysis of Variance part of Table 14.2. From this table, SSE = 36,207.