Applied Categorical and Count Data Analysis

Preface This book focuses on statistical analysis of discrete data, including categorical and count outcomes. Discrete variables are abundant in practice, and knowledge about and ability to analyze such data is important for professionals and practitioners in a wide range of biomedical and psychosocial research areas. Although there are some excellent books on this general subject such as those by Agresti (2002, 2007); Long (1997); Long and Freese (2006), and Stokes et al. (2009), a book that includes models for longitudinal data, real data examples with detailed programming codes, as well as intuitive explanations of the models and their interpretations and di erences thereupon will compliment the repertoire of existing texts. Motivated by the lack of such a text, we decided to write this book ve years ago when preparing a graduate-level biostatistics course on this topic for students within a medical school setting at the University of Rochester. The lecture notes from which this book has evolved havebeen used for the course over the past ve years. In addition to the classic concepts such as contingency tables and popular topics such as logistic and Poisson regression models, as covered by most available textbooks on categorical data analysis, this book also includes many modern topics. These include models for zero modi ed count outcomes, longitudinal data analysis (both parametric and semi-parametric), reliability analysis, and popular methods for dealing with missing values. More importantly, programming codes are provided for all the examples in the book for the four major software packages, R, SAS, SPSS, and Stata, so that when reading the examples readers can immediately put their knowledge--