Customer Reviews

Bayesian Statistical Modelling (Wiley Series in Probability and Statistics - Applied Probability and Statistics Section)

5 star:		(3)
4 star:		(0)
3 star:		(1)
2 star:		(0)
1 star:		(0)

 

 

Congdon presents a very nice and modern treatment of Bayesian methods and models emphasizing implementation using BUGS or WINBUGS. The book covers Bayesian models for regression including linear, log-linear, robust and nonparametric regression. Covers association and classification, mixture models, latent variables, problems of missing data, survival analysis, hierarchical models for pooling information, time series and other correlated data methods (e.g. spatial processes), multivariate analysis, growth curves and model assessment criteria.
The book is loaded with techniques and applications covering a wide variety of topics with reasonable depth.

It also has a very large bibliography with many very relevant and useful references. But there is also a negative side to the bibliography. It was not carefully proofread and there are some annoyances as you will see the same reference listed two, three or more times in the bibliography. Also for such a nice reference text it should have included an author index as well as an ordinary index.

Gibbs sampling is one of the primary estimation techniques in the book but the details are put off until section 10.1 where we get a nice introduction to Gibbs sampling and also the Metropolis algorithm with several excellent references.

This is a good book to start implementing Bayesian methods through the MCMC technique. It contains mostly medical applications which is a nice feature for biostatisticians.

One of the reasons that I am giving this book such a low review is that it's not clear from the book's title, preface, or blurb on the back cover, nor from the first chapter what the purpose of this book and its intended audience are. The back cover is outright misleading; it calls this book an "introductory book on Bayesian modeling techniques". In my opinion, this book seems to be aimed at researchers who already have a strong mastery of most of the techniques used in this book and want a comprehensive overview of the literature as well as a philosophically-sound guide of how to put this theory to use.

The book is quite well-written. The prose is clear, and the author uses just the right amount of mathematical notation and graphs. The author has a comprehensive understanding of the literature, and gives numerous and appropriate references both to justify his points, and to point the reader to further reading.

My objection to this book is that it is not a good place to go to learn any of the material--especially the theoretical material. There is not much exposition of the theory; in contrast to many books, this book provides a good justification of the "why" but a poor explanation of the "how". While I deeply appreciate the "why", I am not satisfied without both. One can have a fairly solid general background in statistics and yet still have trouble understanding this book: this book requires a solid prior background in Bayesian inference, MCMC sampling, and the appropriate areas of regression. This book would not be very useful to people who did not already know most of the material contained in it.

In my opinion, this book would be greatly improved by being more honest and forward about the purpose, intended audience, and required background. I would also deeply appreciate it if the authors would do a better job of pointing to references which are better places to learn this material--most of the references are to the primary literature, and although they do reference a few very good textbooks, there are a ton of key subjects for which they do not point the reader to any good learning sources. I might be convinced to give this book five stars if the author could address these shortcomings.

The book is simply awesome - it covers a very wide range of topics with pretty in-depth discussion in a practical way. Combined with the freely available WinBUGS programs on the author's site, this would be pretty hard to beat. I have read quite a few Bayesian analysis books and this is definitely one of the best or simply the best. Looking forward to reading the author's latest book just published.

Above and beyond rating for timeliness from seller. Would give six stars if I could. Easy communication and clear accurate product condition.