This entry-level text offers clear and concise guidelines on how to select, construct, interpret, and evaluate count data. Written for researchers with little or no background in advanced statistics, Modeling Count Data presents treatments of all major models using numerous tables, insets, and detailed modeling suggestions. It begins by demonstrating the fundamentals of linear regression and works up to an analysis of the Poisson and negative binomial models, and to the problem of overdispersion. Examples in Stata, R, and SAS code enable readers to adapt models for their own purposes, making the text an ideal resource for researchers working in public health, ecology, econometrics, transportation, and other related fields.
1. Varieties of count data
2. Poisson regression
3. Testing overdispersion
4. Assessment of fit
5. Negative binomial regression
6. Poisson inverse Gaussian regression
7. Problems with zeros
8. Modeling under-dispresed count data – generalized Poisson
9. Complex data: more advanced models
Appendix A. SAS code
Joseph Hilbe is a solar system ambassador with NASA's Jet Propulsion Laboratory, California Institute of Technology; an adjunct professor of statistics at Arizona State; an emeritus professor at the University of Hawaii; and a statistical modeling instructor for Statistics.com, a web-based continuing-education program in statistics. He is the author of several books on statistical modeling and serves as the coordinating editor for the Cambridge University Press series Predictive Analytics in Action.
"This is a first-rate introductory book for modeling count data, a key challenge in applied statistics. Hilbe's experience and affability shine in the text. His careful emphasis on establishing the defensibility of models, for example, in the face of overdispersion, will greatly benefit the beginning statistician. His clear informal explanations of important and complicated statistical principles are invaluable."
– Andrew Robinson, University of Melbourne
"The negative binomial model is the foundation for modern analysis of count data. Joe Hilbe's work collects a vast wealth of technical and practical information for the analyst. The theoretical developments and thoroughly worked applications use realistic data sets and a variety of computer packages. They will provide to the practitioner an indispensable guide for basic single-equation count data regressions and advanced applications with recently developed model extensions and methods."
– William Greene, New York University
"This book is a great introduction to models for the analysis of count data. Using the Poisson GLM as the basis, it covers a wide range of modern extensions of GLMs, and this makes it unique. Potentially complex models (which are often needed when analyzing real data sets) are presented in an understandable way, partly because data sets and software code are provided. I reckon that this volume will be one of the standard GLM reference books for many years to come."
– Alain F. Zuur, Highland Statistics Ltd