Categorical Data Analysis
Course Syllabus
Instructor: Sewon Park
Email: swpark0413@sookmyung.ac.kr
Semester: Fall / 2025
Class Time & Location: Tuesdays & Thursdays, 16:30–17:45, Room B116, Changhak B
Office Hours: Tuesdays, 14:30-15:30 or by appointment
Course Description
This course covers the fundamental theories and practical methods of categorical data analysis, which is a core subject in statistical data analysis alongside regression analysis. While regression analysis (and ANOVA) focuses on continuous response variables, categorical data analysis addresses discrete response variables such as binary, multinomial, and count data. We will learn a wide range of methodologies for analyzing categorical outcomes, with emphasis on both theoretical foundations and practical applications.
Learning Objectives
By the end of the course, students will be able to:
- Perform categorical data analyses using R (or Python) and interpret the results from real-world datasets.
- Extend their knowledge of regression analysis to the framework of Generalized Linear Models (GLMs), with an emphasis on categorical response models.
- Understand and compare methods for analyzing binary, multinomial, ordinal, and count data.
- Evaluate model fit, interpret parameter estimates, and apply categorical data analysis techniques to practical data analysis problems.
Prerequisites
- Mathematical Statistics I, II
- Linear Regression
Course Materials
- Textbook:
- Alan Agresti 지음 | 박태성, 이승연 옮김, 범주형 자료분석 개론, 자유아카데미.
- Alan Agresti, An introduction to categorical data analysis, Wiley
Grading Policy
Component | Percentage |
---|---|
Attendance | 5% |
Assignments | 20% |
Midterm Exam | 35% |
Final Exam | 40% |
Weekly Schedule
Week | Topic | Readings / Notes |
---|---|---|
1 | Introduction and Review | Ch. 1 |
2 | Analyzing Contingency Tables I | Ch. 2 |
3 | Analyzing Contingency Tables II | Ch. 2 |
4 | Generalized Linear Models | Ch. 3 |
5 | Logistic Regression | Ch. 4 & Ch. 5 |
6 | Multicategory Logit Models I | Ch. 6 |
7 | Multicategory Logit Models II | Ch. 6 |
8 | Midterm Exam | — |
9 | Analysis of Count Data: Poisson, Overdispersion, Negative Binomial | — |
10 | Analysis of Count Data: Zero-Inflation & Log-Linear Models | — |
11 | Loglinear Models for Contingency Tables and Counts | Ch. 7 |
12 | Models for Matched Pairs | Ch. 8 |
13 | Generalized Estimating Equations (GEE) | Ch. 9 |
14 | Random Effects: Generalized Linear Mixed Models | Ch. 10 |
15 | Final Exam | — |