An Introduction to Generalized Linear Models, Fourth Edition provides a cohesive framework for statistical modelling, with an emphasis on numerical and graphical methods. This new edition of a bestseller has been updated with new sections on non-linear associations, strategies for model selection, and a Postface on good statistical practice.
Like its predecessor, this edition presents the theoretical background of generalized linear models (GLMs) before focusing on methods for analyzing particular kinds of data. It covers Normal, Poisson, and Binomial distributions; linear regression models; classical estimation and model fitting methods; and frequentist methods of statistical inference. After forming this foundation, the authors explore multiple linear regression, analysis of variance (ANOVA), logistic regression, log-linear models, survival analysis, multilevel modeling, Bayesian models, and Markov chain Monte Carlo (MCMC) methods.
- Introduces GLMs in a way that enables readers to understand the unifying structure that underpins them
- Discusses common concepts and principles of advanced GLMs, including nominal and ordinal regression, survival analysis, non-linear associations and longitudinal analysis
- Connects Bayesian analysis and MCMC methods to fit GLMs
- Contains numerous examples from business, medicine, engineering, and the social sciences
- Provides the example code for R, Stata, and WinBUGS to encourage implementation of the methods
- Offers the data sets and solutions to the exercises online
- Describes the components of good statistical practice to improve scientific validity and reproducibility of results.
Using popular statistical software programs, this concise and accessible text illustrates practical approaches to estimation, model fitting, and model comparisons.
Table of Contents
Exponential Family and Generalized
Normal Linear Models
Binary Variables and Logistic Regression
Nominal and Ordinal Logistic Regression
Poisson Regression and Log-Linear Models
Clustered and Longitudinal Data
Markov Chain Monte Carlo Methods
Example Bayesian Analyses
Annette J. Dobson is Professor of Biostatistics at the Univesity of Queensland.
Adrian G. Barnett is a professor at the Queensland University of Technology.
Praise for the Third Edition:
Overall, this new edition remains a highly useful and compact introduction to a large number of seemingly disparate regression models. Depending on the background of the audience, it will be suitable for upper-level undergraduate or beginning post-graduate courses.The comments of Lang in his review of the second edition, that ‘This relatively short book gives a nice introductory overview of the theory underlying generalized linear modelling. …’ can equally be applied to the new edition. … three new chapters on Bayesian analysis are also added. … suitable for experienced professionals needing to refresh their knowledge … .
—Christian Kleiber, Statistical Papers (2012) 53
—Pharmaceutical Statistics, 2011
The chapters are short and concise, and the writing is clear … explanations are fundamentally sound and aimed well at an upper-level undergrad or early graduate student in a statistics-related field. This is a very worthwhile book: a good class text and a practical reference for applied statisticians.
This book promises in its introductory section to provide a unifying framework for many statistical techniques. It accomplishes this goal easily. … Furthermore, the text covers important topics that are frequently overlooked in introductory courses, such as models for ordinal outcomes. … This book is an excellent resource, either as an introduction to or a reminder of the technical aspects of generalized linear models and provides a wealth of simple yet useful examples and data sets.
—Journal of Biopharmaceutical Statistics, Issue 2
This book aims to provide an overview of the key issues in generalized linear models (GLMs), including assumptions, estimation methods, different link functions, and a Bayesian approach. Applications of the book concern different types of data, such as continuous, categorical, count, correlated, and time-to-event data. The book contains theoretical and applicable examples of different type of GLMs. The first five chapters introduce the basics of linear models and the relations between different distributions. The following chapters explain GLMs in respect to different types of link function. One of the most important features of the book is the statistical software codes in each chapter, which make it more practical, as well as the last chapter that focuses on examples of Bayesian analysis.
- Morteza Hajihosseini in ISCB, June 2019