Teaching Data Science as a First Statistics Course to 1,000 Students Per Semester

• Activity Number: 471 - Innovative and Effective Teaching for Large-Enrollment Statistics and Data Science Courses
• Type: Topic Contributed
• Date/Time: Wednesday, August 1, 2018 : 8:30 AM to 10:20 AM
• Sponsor: Section on Statistical Education
• Author(s): John DeNero* and Ani Adhikari
• Companies: University of California, Berkeley and University of California, Berkeley
• Keywords: data science; education

Abstract

Foundations of Data Science is the fastest growing course in UC Berkeley history, with more than 1,000 students enrolling each semester just two years after the course was introduced. We will describe how elements of a classical introductory statistics curriculum are interleaved into a first-year course that also introduces programming and social implications. The course covers fundamental statistics concepts such as sampling, confidence intervals, hypothesis testing, prediction, regression, and regression inference. All topics are illustrated with real-world public data sets that expose students to the challenges of working with large scale data sets, understanding how data were collected, and interpreting quantities correctly.