0
0假设检验详解（Hypothesis Testing Explained）：从第一性原理理解Alpha（α）、Beta（β）、统计功效（Power）、MDE、标准误与样本量。视频为英文讲解，已提供简体中文字幕；内容也涵盖原假设/备择假设、第一类/第二类错误与临界值。
中文技术伴读（含公式、视频截图与常见误解）：
【为什么重新上传】
这期视频最早由我和Statsig数据科学团队在2024年共同制作，并发布在Statsig的YouTube频道。后来Statsig不再使用那个频道，原视频也不再在线，所以我把最终版本重新上传到自己的频道，方便需要的人继续观看。
Hypothesis testing explained visually and from first principles: null and alternative hypotheses, standard error, Type I and Type II errors, alpha, beta, statistical power, minimum detectable effect (MDE), critical values, and sample size.
Many textbooks blur Fisher’s significance testing with the Neyman–Pearson decision framework. This tutorial separates the two, then reconnects the concepts into one coherent experimental design.
You’ll learn:
• Null vs. alternative hypotheses
• Standard deviation vs. standard error
• Type I error, alpha, and critical values
• Type II error, beta, and statistical power
• How sample size changes power and MDE
• Minimum Detectable Effect (MDE)
• Common misconceptions about p-values and “accepting” H₀
This video was originally produced with the Statsig data science team in 2024 and refined through six versions.
00:00 Why hypothesis testing matters
02:46 H₀, alpha, and the critical value
06:41 H₁, beta, and statistical power
09:26 Statistical power in three views
11:23 MDE, standard error, and sample size
14:26 Common misconceptions and practical takeaways
15:41 Conclusion
Presented by Yuzheng Sun, PhD.
