By Xuemao Zhang
Information
Traditionally, statistics courses have primarily focused on classical inferential methods and regression analysis. As the demand for data-driven skills surges in today's world, the integration of machine learning techniques into undergraduate statistics education has become imperative. This presentation explores the integration of machine learning concepts, such as regression models, classifications, and Principal Components Regression (PCR), into undergraduate curricula. Through illustrative examples and case studies, attendees will discover how these methodologies enhance students' understanding of statistical principles and proficiency in analyzing complex datasets. This presentation demonstrates an approach to bridging the gap between traditional statistics and contemporary machine learning, with the goal of empowering undergraduate students with the essential knowledge and skills required to address real-world data analysis challenges. These techniques have been implemented at a public university in PA for computer science, mathematics, and psychology students in Spring 2023 with 8 students. The students were assessed through homework assignments, in class quizzes, two data analysis projects, and a final project.