Monte Carlo Methods in Bayesian Computation (Springer Series in Statistics)

Rating:
Summary: Same writer reviewed book 4 times!
Review: I depend upon the Amazon reviews to help determine whether to purchase a book as most others do. When a reviewer posts four 5 star reviews of the book (out of 7 total) it biases the rating and makes one wonder whether if the reviewer has an agenda or is related to the authors. This may be a great book, but I have no confidence from the rating given here.

Rating:
Summary: Much of the text is verbatim from the papers
Review: I just want to comment that much of the text comes verbatim from the papers cited in the references. At first, I thought that was fine because it appeared only to be from the authors' papers, which are heavily cited, naturally. Then I located one that was not written by the authors. The theory, results, and conclusions were literally lifted off that paper and put into their book (with citation). The same has been true of almost every single paper that I have read referenced from this book.

The references get five stars. The book gives almost no new information, hence the two stars.

Rating:
Summary: extensive book on MCMC
Review: My comment about much of this text being verbatim from papers applies mostly to another text by two of the authors (Bayesian Survival Analysis by Ibrahim, Chen, and Sinha, Springer, 2001). The degree to which the comment is true of Chen et al. (1999) is nowhere near the degree to which it is true of Ibrahim et al. (2001). But, it's not completely false either!

Rating:
Summary: two great books
Review: This is a great book by the authors, covering a wide range of
topics in MCMC. The coverage of the material is deep and novel.
Two of the authors also have published another outstanding book
titled Bayesian Survival Analyis, by Ibrahim et al., which presents
cutting edge and novel methods in the analysis of survival data.
Both books get 5 stars from me. A splendid job by the authors
in writing two very fine books.

Rating:
Summary: two great books
Review: This is an outstanding book on MCMC methods. The book presents
novel and sophisticated methods for carrying out posterior
computations and summarizing posterior quantities of interest using novel MCMC techniques. The authors present a lot of their
groundbreaking work as well as summarizing the work of many others. The book presents a number of complex models used in real and interesting applications in the biomedical sciences. Two of the authors also have wirtten another outstanding book titled Bayesian Survival Analysis (Ibrahim et al., 2001), which presents modern methods for Bayesian survival analysis and provides a comprehensive and thorough treatment of the subject. The authors are to be congratulated on writing two very fine books. Both books get 5 stars from me.

Rating:
Summary: extensive book on MCMC
Review: This is truly an oustanding book on MCMC methods for Bayesian
computation. The authors present a nice balance between technical
developments and applications. It covers several topics not covered by other MCMC books, such as HPD regions, model selection, and density estimation. This book is world class.

Rating:
Summary: special MCMC methods for efficient Bayesian computation
Review: With advances in computing and the rediscovery of Markov Chain Monte Carlo methods and their application to Bayesian methods, there have been a number of books written on this subject in recent years. What then distinguishes this text from the others?

Section 1.1 of the text "Aims" provides the objectives of the book and compares it to the other recent major works. Basically, the authors say that Tanner (1996), Gilks, Richardson and Spiegelhalter (1996), Gamerman (1997), Robert and Casella (1999) and Gelfand and Smith (2000) all offer developments in MCMC sampling. So this text only provides a brief but hopefully sufficient introduction to MCMC sampling. The main objective of the book is to develop more advanced Monte Carlo methods that speed up the computational time for specialized Bayesian problems. Problems of interest to the authors include estimating posterior means, modes and standard deviations, Bayesian p-values, marginal posterir densities, marginal likelihoods, Bayes factors, posterior model probabilities, Bayesian credible intervals (the Bayes analogue to frequentist confidence intervals) and highest posterior probability density intervals.

Chapter 1 sets the stage. It provides the objectives, an outline of the rest of the book and a list of motivating examples that will be used throughout the text.

Chapter 2 then provides the brief introduction to MCMC sampling. Some theory is provided, many useful references are cited and several ideas are well illustrated through examples and figures.

Chapter 3 is also introductory in nature showing how the methods of Chapter 2 can be applied to obtain various estimates based on the approximated posterior probability distribution.

The rest of the book deals with specialized topics and techniques important to Bayesian inference. The book contains a wealth of theory and a good mix of applications and challenging research problems. The authors are experienced contributors to this literature.

It is intended as an advanced graduate course for Ph.D. statistics student in their second or third year of graduate study. It also will serve statistical researchers with an excellent reference both for the practice and development of Bayesian inference. Applications in the area of biostatistics are emphasized but the methods apply to Bayesian statistical inference in all fields.

Rating:
Summary: not a good starting point
Review: You need to be clear what you are looking for. If you have vaguely heard that MCMC (Monte Carlo Markov Chain) methods are a neat way to apply Bayesian ideas to practical problems, and you want to use them, then this is *not* the book for you. Go to the splendid Gilks et al, Markov Chain Monte Carlo in Practice. Also check out BUGS, which is free software, originally written by Gilks and co and improved by many others.

If you want a more general introduction to Bayesian methods, then Gelman et al, Bayesian Data Analysis is excellent.

If you are unclear about the controversies and want to know why the Bayesian approach is correct, and the others are flat wrong, then read Ed Jaynes book.

So what is this book for. Well, I think you have to be a specialist, interested in further development of the techniques, and in the maths. As a previous reviewer has commented (correctly), in that case you probably have easy access to the journal literature and need to think carefully what extra benefits this book gives you.