Note: This page is under construction, and will be updated frequently throughout the term.

Question about "proportional means:" This term applies to some common Poisson regression models, but there is no reference to it in either the lecture notes or the text. See Question (1bviii) in Assignment 8. Re-do the first part of Question 1 and then see if it's clear why this model could be called proportional means.

Final formula sheet is posted below.

Information about the final exam: A page is posted below.

Quiz solutions including Quiz 11 are posted Here

• Course Outline
• Textbook: An introduction to categorical data analysis (2nd ed.) by Alan Agresti. It is available in pdf format free through the U of T library.
• About the Final Exam
• Formula Sheet: This is the formula sheet for the final exam. It will also be provided with Quiz 11.
• Assignments
  1. Assignment 1: Quiz on Friday Sept. 21st
  2. Assignment 2: Quiz on Friday Sept. 28th
  3. Assignment 3: Quiz on Friday Oct. 5th
  4. Assignment 4: Quiz on Friday Oct. 12th
  5. Assignment 5: Quiz on Friday Oct. 19th
  6. Assignment 6: Quiz on Friday Oct. 26th
  7. Assignment 7: Quiz on Friday Nov. 2nd
  8. Assignment 8: Quiz on Friday Nov. 9th
  9. Assignment 9: Quiz on Friday Nov. 16th
  10. Assignment 10: Quiz on Friday Nov. 23d
  11. Assignment 11: Quiz on Friday Nov. 30th
• Lecture Overheads You might want to print these and bring them to class so you can write notes on them during lecture. Some of the lectures are available in a handout version that has the same content but takes less paper.
  1. Introduction
     • Slides (Slightly revised after the lecture)
     • Handout (Not revised)
  2. Multinomial
     • Slides (Edited Oct. 2 after class)
     • Handout
  3. Contingency Tables Part One (Edited Oct. 2 after class)
  4. Tests of Independence with R: Basic large-sample tests (Edited Oct. 2 after class)
  5. Contingency Tables Part Two: Now complete, mistake on slide 30 fixed Oct. 9th after class
  6. Fisher's exact test with R
  7. Regression (review?): Edited Oct. 9th after class
  8. Ordinary Regression with R
  9. Logistic Regression Part One
  10. Logistic Regression with R: Example One
  11. Factorial ANOVA (Back to the normal linear model for a moment)
  12. Logistic Regression with R: Example Two: Interactions
  13. Poisson Regression
  14. Poisson Regression with R
  15. Generalized Linear Models
  16. Multinomial Logit Models: Logistic regression with more than two outcomes.
  17. Multinomial Logit Models with R: Math data
  18. Log-linear models Part 1
  19. Log-linear Models with R Part 1
  20. Log-linear Models with R Part 2: Several ways to read in data.
  21. Conditional independence in log-linear models
  22. Numerical Maximum Likelihood including iterative proportional model fitting
  23. Power and Sample Size for general log-linear models.
  24. Power and Sample Size with R
  25. The End: A bit more on explanatory variables and structural zeros
• R Software
  • Official R website, including download links and instructions.
  • More R Links
  • Introduction to R: A very nice 100-page PDF document. Highly recommended if you are going to be using R for serious work.
• Data sets from homework and lectures.
• Source Code for lecture overheads, homework and other class materials. It's mostly in LaTeX and Openoffice.org format.

All course materials prepared by Jerry (lecture overheads, homework problems, etc.) are licensed under a Creative Commons Attribution-ShareAlike 3.0 Unported License. Source code is available. See the Source Code link above for more information.