Hypothesis Testing - Lecture at The University of Illinois

This is an excerpt from a statistics lecture at the University of Illinois, focusing on hypothesis testing. Hypothesis testing is one of the core tools in data science and statistical inference, widely applied in scientific research, business analytics, machine learning, and other fields. Offered by the Department of Computer Science at the University of Illinois as part of its Data Science Exploration platform, this course aims to help learners build a solid foundation in statistical thinking. The highlight lies in the systematic breakdown of the hypothesis-testing logic chain: from the definitions of null and alternative hypotheses, to the selection of test statistics and the meaning of p-values, and then to significance levels and decision rules—each step building progressively on the last, presented with clear structure. The emphasis is on conceptual understanding rather than mere formula memorization, making it ideal for learners who want to truly "understand the principles." Target audience includes beginners in data science with some background in statistics, students in related majors, and professionals interested in data-driven decision making. Viewing recommendations: follow along with the textbook or your own notes, pay special attention to the practical meaning of p-values and confidence intervals, and reinforce your learning with the exercises at the end of each chapter.