BMTRY 711: Analysis of Categorical Data
Spring 2007


Class Information

Instructor Dipankar Bandyopadhyay
Assistant Professor
Department of Biostatistics, Bioinformatics, and Epidemiology
135 Cannon Street, Suite 305 E 
Medical University of South Carolina

Class Schedule Tuesday, Thursday
1.30 PM - 3.00 PM
Cannon Place, Room # 304 (DB2E Conference Room)

Office Hours Thursdays  3.00 PM - 4.00 PM, or by appointment

Required Texts A. Agresti: Categorical Data Analysis, 2nd Edition, Wiley, 2002

agrestibook

D. Kleinbaum & M. Klein: Logistic Regression: A self-learning text, 2nd Edition, Springer, 2002

kleinbaumbook


General Class Outline and Reading Blocks



  • Introduction (Agresti Chapter 1)
  • Contingency Tables (Agresti Chapters 2, 3)
  • Generalized Linear Models (Agresti Chapter 4, Kleinbaum & Klien Chapters 4)
  • Logistic Regression (Kleinbaum & Klien Chapters 1 - 3, Agresti Chapter 5)
  • Model Building Strategies (Agresti Chapter 6, Kleinbaum & Klien Chapters 6 & 7)
  • Logit Models for Multinomial Responses (Agresti Chapter 7, Kleinbaum & Klien Chapters 9 & 10)
  • Log-linear Models (Agresti Chapter 8)
  • Models for Matched and Correlated Data (Agresti Chapters 10, 11, Kleinbaum & Klien Chapters 8, 11 - 13)

Grading
  • Homework sets and class participation (30% total)
  • Two midterm exams (20% each) Midterm Exam 2                                                             Data (Problem1)
  • Final exam (30%): Inclass May 2 (Wed, 11.30AM-12.30AM)                           

Lecture Notes*

Date Lecture Title
1/9/07 Class Introduction
Lecture 1: Introduction
1/11/07 Lecture 2: Inference on Binomial parameters
1/16/07 Lecture 3: Inference on Multinomial parameters
1/18/07 Lecture 4: Association Measures
1/23/07 Lecture 5: Contingency Tables
1/25/07 Lecture 6: Contingency Tables continued
1/30/07 Lecture 7: Testing Independence
2/01/07 Lecture 8: Summary Measures
2/06/07 Lecture 9: Association Measures in Contingency Tables
2/08/07 Lecture 10: Partitioning Chi Squares/Residual Analysis
2/13/07 Lecture 11: Generalized Linear Models: Introduction
2/15/07   Lecture 12: Generalized Linear Models for Binary Data
2/22/07 Lecture 13: Generalized Linear Models for Poisson Data
2/27/07 Lecture 14: GLM Estimation
3/01/07 Lecture 15: Logistic Regression/Common Odds Ratio (Part 1)
3/06/07 Lecture 16: Logistic Regression/Common Odds Ratio (Part 2)
3/08/07 Lecture 17: Logistic Regression: Homogeneity of OR
3/19/07 Lecture 18: Logistic Regression Continued
Cancer Data
SAS Program
SAS Output (Diagnostics)
3/27/07 Lecture 19: Conditional Logistic Regression
4/03/07 Lecture 20: Polytomous Logit Models
SAS Program
4/05/07 Lecture 21: Polytomous Logit Models Contd
Arthiritis Data
4/10/07 Lecture 22: Log-linear Models
4/17/07 Lecture 23: Log-linear Models Contd
SAS Program
STATA Data
4/19/07 Lecture 24: Log-linear Models for Sparse Data
SAS Code
4/24/07 Lecture 25: Models for Matched Pairs
4/26/07 Lecture 26: Conditional logistic regression for Matched Pairs
4/27/07 Lecture 27: Introduction to Correlated Binary Data
* Printing instruction: The PDF files can be printed more than one slide to a page by accessing the advanced printer options on your printer (not all printers are capable, but the photocopiers are)