知识卡片
统计能力贯穿数据到结论链路
描述、可视化、概率、抽样与推断分别帮助理解观测和表达不确定性。机器学习的计算能力不能消除抽样偏差与估计误差,统计也不限于简单汇总;应按问题选择所需方法。
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
Data scientists should have a strong background in statistics, mathematics, and general computer programming. Good analytical and statistical skills are a prerequisite to the successful application and implementation of data science tools. Besides the simple statistical tools, data science also uses statistical modeling including descriptive analytics and predictive and prescriptive analytics tools modeling for decision-making and predicting future business outcomes. Thus, a combination of mathematical
参考来源
- 位置:《Machine Learning Fundamentals: Concepts, Models, and Applications》第01章《数据科学与机器学习概览》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Machine Learning Fundamentals: Concepts, Models, and Applications/_epub-src/OEBPS/xhtml/12_chapter01.xhtml)
- 结论依据:摘录中关于统计能力贯穿数据到结论链路的定义、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:Data scientists should have a strong background in statistics, mathematics, and general computer programming. Good analytical and statistical skills are a prerequisite to the successful application and implementation of data science tools. Besides the simple statistical tools, data science also uses statistical modeling including descriptive analytics and predictive and prescriptive analytics tools modeling for decision-making and predicting future business outcomes. Thus, a combination of mathematical