This short course presents an overview of generalized linear modeling
(GLM). After introducing basic results for GLMs, we present GLMs for
four types of response variables: continuous responses, binary
responses, multicategory responses, and count responses. Primary
emphasis is on gamma regression for positive, skewed responses,
logistic regression for binary response data, cumulative logit models
for ordinal responses, and negative binomial regression for count
responses. The presentation emphasizes interpretation rather than
technical details. Examples primarily use R, with some examples also
using SAS. The material covered is in Chapters 47 of the book
"Foundations of Linear and Generalized Linear Models" (Wiley, 2015) by
Alan Agresti
Alan Agresti is Distinguished Professor Emeritus of Statistics at the University of Florida. He is author or coauthor of more than 100 articles and seven books, including "Categorical Data Analysis" (3rd
ed. 2013), "Statistics: The Art and Science of Learning from Data"(4th ed. 2016), and "Foundations of Linear and Generalized Linear Models" (2015). He is a fellow of the American Statistical Association and
of the Institute of Mathematical Statistics, Agresti has received an honorary doctorate from De Montfort University in the U.K., and the Statistician of the Year award from the Chicago chapter of the American Statistical Association.
