2nd Edition. — Chapman & Hall/CRC texts in statistical science series, 2002. — 221 p.
The original purpose ofthe book was to present a unified theoretical and conceptual framework for statistical modeling in a way that was accessible to undergraduate students and researchers in other fields. This new edition has been expanded to include nominal (or multinomial) and ordinal logistic regression, survival analysis and analysis of longitudinal and clustered data.
Although these topics do not fall strictly within the definition of generalized linear models, the underlying principles and methods are very similar and their inclusion is consistent with the original purpose ofthe book.
The new edition relies on numerical methods more than the previous edition did. Some of the calculations can be performed with a spreadsheet while others require statistical software. There is an emphasis on graphical methods for exploratory data analysis, visualizing numerical optimization (for example, of the likelihood function) and plotting residuals to check the adequacy of models.
Model Fitting
Exponential Family and Generalized Linear Models
Estimation
Inference
Normal Linear Models
Binary Variables and Logistic Regression
Nominal and Ordinal Logistic Regression
Count Data, Poisson Regression and Log-Linear Models
Survival Analysis
Clustered and Longitudinal Data
Software