Generalized linear models and extensions (Q2889606)

A previous edition of this book appeared in 2007 [Zbl 1242.62077]. This new edition includes new software, a discussion of Poisson inverse Gaussian and zero-inflated Poisson, an enhanced generalized Poisson command, a new zero-inflated generalized Poisson command, a censored Poisson command, and a generalized negative binomial. More information is provided on the Akaike information criterion (AIC) and Bayesian information criterion (BIC), including a command providing the advanced post-estimation fit statistics for nonnested models. Various examples are included to illustrate estimation results. It is shown how to construct synthetic Monte Carlo models for binomial and major count models. A discussion is added of marginal effects and discrete change for generalized linear models (GLMs).NEWLINENEWLINEThe book under review is a nice textbook on GLMs and a thorough handbook of advice for researchers, e.g., from medicine. The authors use the book as the required text for a web-based six-week course.NEWLINENEWLINEContents: 1. Introduction. Part I. Foundations of generalized linear models. 2. GLMs. 3. GLM estimation algorithms. 4. Analysis of fit. 5. Data synthesis. Part II. Continuous response models. 6. The Gaussian family. 7. The gamma family. 8. The inverse Gaussian family. 9. The power family and link. Part III. Binomial response models. 10. The binomial-logit family. 11. The general binomial family. 12. The problem of overdispersion. Part IV. Count response models. 13. The Poisson family. 14. The negative binomial family. 15. Other count data models. Part V. Multinomial response models. 16. The ordered-response family. 17. Unordered-response family. Part VI. Extensions to the GLM. 18. Extending the likelihood. 19. Clustered data. Part VII. Stata software. 20. Programs for Stata.