Applied Linear Models
Linear models permeate statistics. They provide a foundation for applications ranging from modeling observational data to inference in designed experiments to spatial statistics and time series analysis to predictive modeling and more. This course is an introduction to linear models covering standard topics in model specification, estimation, inference, diagnostics, transformations, and several important extensions.
Instructor: Trevor Ruiz (he/him) [email]
Class meetings: TR 12:00pm–1:50pm in 180-272
Office hours: TR 2:30pm–4:00pm in 25-236
Final project due: Thursday 12/17/26 3:30pm
A tentative schedule for the term and detailed course policies can be found in the [course syllabus]. Please note the syllabus is subject to change. Readings, assignments, and materials (notes, scripts, etc.) will be posted below on a rolling basis.
Week 1 (8/24)
Regression and linear algebra review; random variables and random vectors
Week 2 (8/31)
Least squares estimates and their properties
Week 3 (9/7)
Inference in regression and model diagnostics
Week 4 (9/14)
Transformations; unusual observations
Week 5 (9/21)
An end-to-end analysis; midterm 1
Week 6 (9/28)
The general linear model
Week 7 (10/5)
F tests
Week 8 (10/12)
Simulation-based inference; polynomial and nonlinear models
Week 9 (10/19)
Categorical predictors and interactions
Week 10 (10/26)
Variable selection
Week 11 (11/2)
Variable selection cont’d; midterm 2