Each week, classes will be a mix of lecture, class discussion, and short activities.

  • You should bring your laptop with you to every class period. We will be using R and RStudio extensively in this course. In particular, students are encouraged to write homework assignments in R Markdown and compile to pdf for the submission.
  • Assigned readings for each week are posted. Whether you learn better by reading prior to lecture, or hearing a lecture prior to reading is up to you.
  • Weeks will typically alternate between homework assignments and in-class quizzes, with homework due dates and quizzes falling on Thursdays.
    • Homework assignments should be submitted in D2L by 11pm on the due date.
    • Each quiz will cover the content from the previous week’s homework, e.g., Quiz 1 will cover content from Homework 1.

Week 1 (Jan 19–21)

Course Overview

Week 2 (Jan 24–28)

Content

  • Probability distributions for categorical data: binomial, multinomial, negative binomial
  • Asymptotic inference for one and two proportions
  • Exact (binomial) inference for one proportion
  • Maximum likelihood estimation
  • Types of sampling and studies
  • Probability structure for \(I\times J\) contingency tables

Assigned readings

  • Chapter 1 Sections 1.1–1.3, 1.6
  • Chapter 2 Section 2.1

Homework/Quiz

Week 3 (Jan 31–Feb 4)

Content

  • Asymptotic inference for \(2\times 2\) tables: difference in proportions, relative risk, odds ratio

Assigned readings

  • Chapter 2 Sections 2.2–2.3

Thursday

Homework/Quiz

  • Quiz 1 in class Thur Feb 3

Week 4 (Feb 7–11)

Content

  • Randomization tests for \(2\times 2\) tables
  • Fisher’s Exact Test for \(2\times 2\) tables
  • Chi-squared tests of independence for \(I\times J\) contingency tables
  • Association in three-way tables

Assigned readings

  • Chapter 2 Sections 2.4, 2.6–2.7

Homework/Quiz

  • Homework 2 (Rmd) due Thur Feb 10 by 11pm — types of sampling and studies, asymptotic inference for \(2\times 2\) tables, randomization tests, Fisher’s Exact Test

Week 5 (Feb 14–18)

Content

  • Components of a generalized linear model (GLM)
  • GLMs for binary data

Assigned readings

  • Chapter 3 Sections 3.1–3.2
  • Chapter 4 Sections 4.1–4.6
  • Chapter 5 Section 5.3

Thursday

  • Quiz 2 only

Homework/Quiz

  • Quiz 2 in class Thur Feb 17

Week 6 (Feb 21–25)

Content

  • GLMs for binary data (continued)

Assigned readings

  • Continued from last week

Tuesday

Thursday

Homework/Quiz

  • Homework 3 (Rmd) due Thur Feb 24 by 11pm — chi-squared tests of independence, three-way tables, components of a GLM

Week 7 (Feb 28–Mar 4)

Content

  • Logistic regression with categorical predictors

Assigned readings

  • Continued from last week

Thursday

Homework/Quiz

  • Quiz 3 in class Thur Mar 3

Week 8 (Mar 7–11)

Content

  • GLMs for count data
  • Model fitting, selection and diagnostics for GLMs

Assigned readings

  • Chapter 3 Sections 3.3–3.5
  • Chapter 5 Sections 5.1–5.3

Tuesday

Thursday

  • Homicides and gun registraction Poisson regression example (Rmd) (html) (updated 3/22 and 3/24)
  • In-class notes

Homework/Quiz

  • Homework 4 (Rmd) due Thur Mar 10 by 11pm in Gradescope — GLMs for binary data (logistic regression)

Week 9 (Mar 21–25)

Content

  • GLMs for count data (continued)
  • Model fitting, selection and diagnostics for GLMs

Assigned readings

  • Continued from last week

Tuesday

Thursday

Homework/Quiz

  • Quiz 4 in class Thur Mar 24

Week 10 (Mar 28–Apr 1)

Content

  • Model fitting, selection and diagnostics for GLMs (cont)

Assigned readings

  • Chapter 6 Sections 6.1–6.2

Homework/Quiz

  • Homework 5 (Rmd) due Thur Mar 31 by 11pm — GLMS for Poisson regression, model fitting, selection and diagnostics for GLMs

Week 11 (Apr 4–8)

Content

  • Multicategory logit models (cont)

Assigned readings

  • Chapter 8 Sections 8.1, 8.3, 8.5

Homework/Quiz

  • Quiz 5 in class Thur Apr 7

Project Deadline

  • Data analysis proposal due by 11pm Friday Apr 8 in Gradescope.

Week 12 (Apr 11–15)

Content

  • Modeling correlated data
    • Models for matched pairs
    • Marginal models (GEEs)
    • Generalized linear mixed models (GLMMs)

Assigned readings

  • Chapter 8 Sections 8.1–8.2 (skip 8.3–8.6)
  • Chapter 9 Sections 9.1–9.2 (skip 9.3–9.5)
  • Chapter 10 Sections 10.1–10.2 (skip 10.3–10.5)

Tuesday

Thursday

Homework/Quiz

  • Homework 6 (Rmd) due Mon Apr 18 by 11pm — baseline and cumulative logit models for multinomial data

Week 13 (Apr 18–22)

Content

  • Modeling correlated data (continued)

Assigned readings

  • Continued from last week

Tuesday

Thursday

  • Correlated data slides and epilepsy example (continued)
  • In-class notes

Homework/Quiz

  • Quiz 6 in class Thur Apr 21

Project Deadline

  • Draft report due by 11pm Friday Apr 22 in Gradescope.

Week 14 (Apr 25–29)

Content

  • Modeling correlated data (continued)
  • GLM leftovers:
    • Residual diagnostics
    • Dealing with missing data

Assigned readings

  • Continued from last week
  • Some content not in textbook

Tuesday

  • Class cancelled

Thursday

Correlated binary data example:

Homework/Quiz

  • Homework 7 (Rmd) due Thur Apr 28 by 11pm — population-averaged models (i.e., marginal models, GEEs), subject-specific models (i.e., generalized linear mixed effects models)

Project Deadline

  • Peer assessments due by 11pm Friday Apr 29 in Gradescope.

Week 15 (May 2–6)

Content

  • Classification and clustering

Assigned readings

  • Review Chapter 4 Section 4.6
  • Chapter 11 Sections 11.1–11.3

Homework/Quiz

  • Quiz 7 in class Thur May 5 (make-up quiz only)

Project Deadline

  • Final report due by 11pm Friday May 6 in Gradescope.

Final Exam Week

Take-home final exam

Released Friday, May 6. Due by 11pm Wednesday, May 11 in Gradescope.

Project presentations

Thursday, May 12 8:00–9:50am