Data come from a variety of sources: sometimes from planned experiments or designed surveys, sometimes by less organized means. In this course we’ll explore the kinds of models and predictions that we can make from both kinds of data, as well as design aspects of collecting data. We’ll focus on model building, especially multiple regression, and talk about its potential to answer questions about the world — and about its limitations. We’ll emphasize applications over theory and analyze real data sets throughout the course.
Format: lecture; Introductory lectures will be available asynchronously as text and video; synchronous sessions will discuss questions from lecture, dive further into the material, and work on examples. You'll use chat and discussion boards to build community, study with classmates, and ask questions outside of class time. The professor and TAs will also offer optional synchronous office hours/review sessions.
Grading: yes pass/fail option,
yes fifth course option
Homework problems; quizzes; a final project (on a topic that interests you!). You'll be given the opportunity to assess your own work and resubmit/reattempt assignments as you gain mastery of a topic. Participation matters! Engagement with your peers is an important part of learning, of being a statistician in the Real World...and of your evaluation in this course. While your assignments will be submitted (and graded) individually, you'll be responsible for giving and receiving peer feedback, contributing to live and online discussions, and working together with classmates on practice problems.
AP Statistics 4 or 5, or STAT 101, or STAT 161, or STAT 201, or permission of instructor
Prospective Statistics majors and more senior students
students with a 4 on the AP Stats exam should contact the department for proper placement
This course uses mathematical tools and computing programs to create models, make predictions, assess uncertainty, and describe data. We'll also emphasize choosing appropriate mathematical tools and interpreting their results in a real-world context.