# STA 4504-5503: CATEGORICAL DATA METHODS

### Instructor

Alan Agresti, Department of Statistics
### Office Hours

204 Griffin-Floyd Hall: Monday and Wednesday
3-5 pm, and by appointment
### Contact Information

Phone number: (352) 273-2981, e-mail aa@stat.ufl.edu

### Teaching Assistant

Quan Tran, 117D Griffin-Floyd, e-mail
quandtran@stat.ufl.edu, office hours Monday, Wednesday, Friday 2
- 4 pm and by appointment.
### Homework assignments

1. Due Friday, January 15: Chapter 1, exercises 1-4, 8, 12

2. Due Wednesday, January 27: Chapter 2, exercises 2, 3, 5-8, 12,
17-19

3. Due Friday, February 5: Chapter 2, exercises 29, 33-36, 39;
Chapter 3, exercises 1, 2, 22ab

4. Due Friday, February 12: Chapter 3, exercises 5, 9, 11-13,
16; Chapter 4, exercises 1, 4

5. Due Friday, February 19: Chapter 4, exercises 2, 8, 11, 16-17, 28, 37

6. Due Friday, March 5: Chapter 4, exercises 19, 21, 23, 24;
Chapter 5, exercises 4, 15

7. Due Friday, March 19: Chapter 5, exercises 19, 22, 30; Chapter
6, exercise 1

8. Due Friday, March 26: Chapter 6, exercises 3, 5, 6, 7, 12, 22abd

9. Due Friday, April 2: Chapter 8, exercises 2, 4, 20ac; Chapter 9,
exercise 3

10. Due Friday, April 9: Chapter 9, exercises 4, 7, 18, class
exercise on transitional model for insomnia study

11. Due Wednesday, April 21: Chapter 7, exercises 5(a-c), 6, 7, 27

### Outline of course notes:

### Data Sets:

### Link to the General Social Survey

GSS

### Summary of software

SAS programs and data sets from the text are available in the
appendix of the text, starting on p. 332, and at
SAS
programs.

You can get SAS for your home PC with a one-year license through
the Software Licensing
Services.

The CIRCA handout "SAS for
Windows" is useful for getting started. It can also be helpful to
use a primer such as "The Little SAS Book: A Primer" by L. Delwiche
and S. Slaughter or "SAS System for Elementary Statistical Analysis"
by S. Schlotzhauer and R. Littell.

The SAS/STAT User's Guide contains documentation about procedures.
For procedures pertaining to categorical data analysis, go
to SAS
Online Support and click on the SAS/STAT User's Guide and then on
"Introduction to Categorical Data Analysis Procedures". There you can
find all the detail you need about PROCs we use in this course, such
as PROC GENMOD, PROC LOGISTIC, and PROC FREQ. For examples of using
SAS for categorical data analyses for many data sets in the first
edition of the text "An Introduction to Categorical Data Analysis",
see the useful site set up by
the UCLA
Statistical Computing Center. SAS also has a specialized manual
available for purchase, "Categorical Data Analysis Using the SAS
System" by M. Stokes, C. Davis, and G. Koch (2nd ed., 2000).

R is free software, popular among
statisticians because of its power and flexibility but harder to learn
to use. It is an open source version of S-Plus, and many S-Plus
functions also work in R. At
website
for Dr. Chris Bilder the link to R has examples of the use
of R for most chapters of the text. For more detailed information,
a comprehensive manual prepared by
Dr. Laura Thompson shows how to use R and S-Plus to conduct all
the types of analyses presented in this course (although the
organization in her manual follows my more advanced text,
Categorical Data Analysis). You can get a copy of this at
Laura Thompson S
manual for CDA. Thanks very much to Dr. Thompson and to
Dr. Bilder for providing these helpful resources, which I highly
recommend to anyone using R in this course.
For other useful information and links about R and S-Plus, see the
homepage of the UF
professor Dr. Brett
Presnell. Dr. Presnell also has a page
on
R for Categorical Data Analysis from when he taught STA 4504-5503
that has many examples of the use of R. Some of these are for data
sets in the text for this course. For yet other details about R, see
the R web site . This
includes a link to manuals, such as "An Introduction to R", and to the
archives in the Comprehensive R Archive Network (CRAN).

At software
for CDA I have summarized where to go on the SPSS ANALYZE
menu to get access to various methods discussed in the course.
You can get a student version of SPSS at the bookstore or a
one-year license through
the Student Home-Use
Program.

At software for
CDA there are some links. For examples of using Stata for
categorical data analyses for many data sets in the first edition of
the text "An Introduction to Categorical Data Analysis", see the
useful site set up by
the UCLA
Statistical Computing Center.

Here is a sample of the types of
questions (pdf file) you will see on Exam 1. There will be a
combination of true-false or multiple-choice questions as well as
problems. Some problems may come directly from the homework
exercises. The problems put main emphasis on interpretation, rather
than calculation. A formula page is attached to the back of the exam
so you do not feel it necessary to memorize formulas. Here is
a sample of the types of questions (pdf
file) you will see on Exam 2. There will be
some problems like these but also many true-false questions to test
your understanding of the concepts.
### Exam 1 Formula page (PDF file;
this page will be attached to the exam)

### Exam 2 Formula page (PDF file; this
page will be attached to the exam)

Back to Alan Agresti's Home Page