Categorical Data Analysis

Website for CATEGORICAL DATA ANALYSIS, 2nd edition

For the second edition of Categorical Data Analysis by Alan Agresti (Wiley, 2002), this site contains (1) information on the use of other software (such as R and S-plus, Stata, SPSS, StatXact and LogXact) not covered in Appendix A of the text (which discusses SAS in some detail), (2) data sets for examples in the form of complete SAS programs for conducting the analyses, (3) data sets used in some of the homework exercises, (4) short answers for many of the odd-numbered exercises, (5) extra exercises, and (6) corrections of errors in early printings of the book. Also, there's (7) a review paper about Bayesian methods for categorical data analysis.

1. Software for categorical data analyses: Here is a file containing information and links for several software packages.

Software

Dr. Laura Thompson has prepared a detailed manual on the use of R or S to conduct all the analyses in this text. You can get a copy of this excellent resource at Laura Thompson R and S manual for CDA. Thanks very much to Dr. Thompson for providing this manual.

2. Primary datasets: For data sets for many of the main examples in the text, in the form of SAS programs for conducting the analyses, click on

Primary datasets

3. Other datasets not shown in text: Here is a pdf file of

other datasets used in some of the homework exercises for which tables are not shown in the text.

Here is a html file of these

other datasets.

4. Selected answers: Here is a pdf file of short

solutions for many of the odd-numbered exercises at the ends of the chapters:

5. Additional exercises: Here is a pdf file containing

Extra exercises

6. Corrections: Here is a pdf file showing

corrections of typos/errors in the second edition.

7. Finally, for those of you with interest in the Bayesian approach to inference -- I had intended to include a chapter in the second edition on Bayesian analyses for categorical data analysis (to beef up the short section in Chapter 15), but the book just became too long. However, David Hitchcock (Statistics Dept., Univ. of South Carolina) and I have written a survey paper about such methods:

Bayesian inference for categorical data analysis: A survey

A slightly shorter version of this technical report has appeared in the journal of the Italian Statistical Society, Statistical Methods and Applications, in 2005 (volume 14, pages 297-330)