|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/testing-statistical-hypotheses-in-data-science-with-python-3/
课程评论：没有评论
课程名称：使用Python 3进行数据科学中的统计假设检验 课程概述： 本课程旨在弥补理解统计假设检验与有效应用之间的差距，重点利用Python的强大功能对真实世界的数据集进行假设检验。学生将获得可直接应用于专业和学术环境的实践经验。 先决条件： 参加本课程需要掌握假设检验的基础理论，包括零假设与备择假设、显著性水平、检验统计量和p值等概念。如果您对这些概念感到熟悉，就可以开始以编程方式应用它们。 您将学到的内容： 课程中，我们将探索多种统计假设检验方法，包括： - 单样本均值检验：测试某个总体的均值（如每日平均卡路里摄入量）是否等于指定值。 - 两样本均值检验：比较两个独立组的均值（如两种不同药物患者的平均血压）。 - 单样本比例检验：测试某个总体的比例（如喜欢某种产品的人数百分比）是否等于指定值。 - 两样本比例检验：比较两个独立组的比例（如两座城市中吸烟者的百分比）。 - 配对检验：测试配对数据的差异（如治疗组的前后评分）。 - 方差分析（ANOVA）：比较三个以上组的均值（如三种不同饮食的有效性）。 - 卡方检验：测试分类变量之间的独立性（如性别与产品偏好）。 - 非参数检验：如Mann-Whitney U检验、Kruskal-Wallis检验等，适用于不满足参数检验假设的数据集。 您将学习如何制定假设、计算检验统计量、识别拒绝区域，并得出有意义的结论，所有这些都将使用Python进行实现。 为什么要参加本课程？ - 动手学习：每个概念都结合健康、商业、教育、工程等相关的实例数据进行说明。 - 实用工具：您将使用Python Jupyter Notebook编写代码。必要时，假设使用LaTeX清晰地阐述统计假设。 - 专家指导：课程由一位在工程、健康和商业背景下应用统计方法超过20年的数据科学家和统计学家授课。 - 内容全面：本课程专注于假设检验，确保对该主题的深入掌握。 谁应该参加本课程？ 本课程特别适合于： - 进行临床研究的健康研究人员。 - 通过进行假设检验从数据中得出结论的数据科学家和分析师。 - 应用高级检验方法的统计学家。 - 验证过程性能的工程师。 如果您的工作涉及假设检验和数据解读，本课程将赋予您自信地使用Python分析统计问题的技能。
Course DescriptionThis course is designed to bridge the gap between understanding statistical hypothesis testing and applying it effectively using Python. It focuses on leveraging Python's capabilities to perform hypothesis testing on real-world datasets, offering students practical experience that can be directly applied in professional and academic settings.PrerequisitesA strong foundation in the theory of hypothesis testing is essential. This includes familiarity with concepts such as null and alternative hypotheses, significance levels, test statistics, and p-values. If you're comfortable with these concepts, you're ready to dive into applying them programmatically.What You Will LearnThroughout the course, we explore a variety of statistical hypothesis tests, both parametric and non-parametric, including:One-sample tests for means:: Testing whether the mean of a population (e.g., average daily calorie intake) equals a specified value.Two-sample tests for means: Comparing the means of two independent groups (e.g., average blood pressure of patients on two different medications).One-sample test for proportions: Testing whether the proportion of a population (e.g., the percentage of people who prefer a certain product) equals a specified value.Two-sample test for proportions: Comparing the proportions of two independent groups (e.g., the percentage of smokers in two different cities).Paired tests: Testing differences in paired data (e.g., before-and-after scores of a treatment group).ANOVA (Analysis of Variance): Comparing the means of more than two groups (e.g., effectiveness of three different diets).Chi-square tests: Testing for independence between categorical variables (e.g., gender and preference for a product).Non-parametric tests: Mann-Whitney U, Kruskal-Wallis, and others for datasets that do not meet parametric test assumptions.You'll learn how to formulate hypotheses, calculate test statistics, identify rejection regions, and draw meaningful conclusions-all using Python.Why Take This Course?Hands-On Learning: Every concept is illustrated with examples data relevant to health, business, education, engineering, etc.Practical Tools: You'll use Python Jupyter notebooks to write code. Where needed, the hypotheses are clearly well written using LaTeX to clearly document statistical hypotheses.Expert Instruction: The course is taught by a Data Scientist and Statistician with over 20 years of experience applying statistical methods in engineering, health, and business contexts.Comprehensive Content: This course focuses exclusively on hypothesis testing, ensuring depth and mastery of the topic.Who Should Take This Course?This course is ideal for:Health researchers performing clinical studies.Data Scientists and Analysts who draw conclusions from data by carrying out hypotheses testing.Statisticians applying advanced testing methods.Engineers validating process performance.If your work involves testing hypotheses and interpreting data, this course will equip you with the skills to confidently analyze statistical problems using Python.
