- Save 10% on selected children’s books, compliments of Amazon Family Promotion exclusive for Prime members .
The Bayesian Choice: A Decision-Theoretic Motivation (Springer Tracts in Natural Philosophy) Hardcover – 1 Feb 1997
There is a newer edition of this item:
Special offers and product promotions
Customers who viewed this item also viewed
What other items do customers buy after viewing this item?
Enter your mobile number or email address below and we'll send you a link to download the free Kindle App. Then you can start reading Kindle books on your smartphone, tablet, or computer - no Kindle device required.
To get the free app, enter your mobile phone number.
If you are a seller for this product, would you like to suggest updates through seller support?
From the reviews of the second edition:
SHORT BOOK REVIEWS
"The text reads fluently and beautifully throughout, with light, good-humoured touches that warm the reader without being intrusive. There are many examples and exercises, some of which draw out the essence of work of other authors. Each chapter ends with a "Notes" section containing further brief descriptions of research papers. A reference section lists about eight hundred and sixty references. Each chapter begins with a quotation from "The Wheel of Time" a sequence of books by Robert Jordan. Only a few displays and equations have numbers attached. This is an extremely fine, exceptional text of the highest quality."
ISI Short Book Reviews, April 2002
JOURNAL OF MATHEMATICAL PSYCHOLOGY
"This book is an excellent introduction to Bayesian statistics and decision making. The author does an outstanding job in explicating the Bayesian research program and in discussing how Bayesian statistics differs form fiducial inference and from the Newman-Pearson likelihood approach…The book would be well suited for a graduate-level course in a mathematical statistics department. There are numerous examples and exercises to enhance a deeper understanding of the material. The writing is authoritative, comprehensive, and scholarly."
"This book is a publication in the well-known Springer Series in statistics published in 2001. It is a textbook that presents an introduction to Bayesian statistics and decision theory for graduate level course … . The textbook contains a wealth of references to the literature; therefore it can also be recommended as an important reference book for statistical researchers. … for those who want to make a Bayesian choice, I recommend that you make your choice by getting hold of Robert’s book, The Bayesian Choice." (Jan du Plessis, Newsletter of the South African Statistical Association, June, 2003)
"This is the second edition of the author’s graduate level textbook ‘The Bayesian choice: a decision-theoretic motivation.’ … The present book is a revised edition. It includes important advances that have taken place since then. Different from the previous edition is the decreased emphasis on decision-theoretic principles. Nevertheless, the connection between Bayesian Statistics and Decision Theory is developed. Moreover, the author emphasizes the increasing importance of computational techniques." (Krzysztof Piasecki, Zentralblatt MATH, Vol. 980, 2002)--This text refers to an alternate Hardcover edition.
From the Back Cover
Winner of the 2004 DeGroot Prize
This paperback edition, a reprint of the 2001 edition, is a graduate-level textbook that introduces Bayesian statistics and decision theory. It covers both the basic ideas of statistical theory, and also some of the more modern and advanced topics of Bayesian statistics such as complete class theorems, the Stein effect, Bayesian model choice, hierarchical and empirical Bayes modeling, Monte Carlo integration including Gibbs sampling, and other MCMC techniques. It was awarded the 2004 DeGroot Prize by the International Society for Bayesian Analysis (ISBA) for setting "a new standard for modern textbooks dealing with Bayesian methods, especially those using MCMC techniques, and that it is a worthy successor to DeGroot's and Berger's earlier texts".
Christian P. Robert is Professor of Statistics in the Applied Mathematics
Department at the Université Paris Dauphine, and Head of the Statistics Laboratory at the Center for Research in Economics and Statistics (CREST) of the National Institute for Statistics and Economic Studies (INSEE) in Paris. In addition to many papers on Bayesian statistics, simulation methods, and decision theory, he has written four other books, including Monte Carlo Statistical Method (Springer 2004) with George Casella and Bayesian Core (Springer 2007) with Jean-Michel Marin. He has served or is serving as associate editor for the Annals of Statistics, Bayesian Analysis, the Journal of the American Statistical Association, Statistical Science, and Sankhya. and is editor of the Journal of the Royal Statistical Society (Series B) from 2006–2009. He is a fellow of the Institute of Mathematical Statistics, and received the 1995 Young Statistician Award of the Société de Statistique de Paris.
Review of the second edition:
"The text reads fluently and beautifully throughout, with light, good-humoured touches that warm the reader without being intrusive. There are many examples and exercises, some of which draw out the essence of work of other authors. Only a few displays and equations have numbers attached. This is an extremely fine, exceptional text of the highest quality." (ISI Short Book Reviews)--This text refers to an alternate Hardcover edition.
Top customer reviews
At the time of writing this review, the 2nd edition (2001) and the paperback(2007) have been published for more than 10 years.
The book is very, very comprehensive for its size, at the time it was published. As such, it's understandable that several details are not going to be touched by the author. From the title one can gather that the perspective will be more theory oriented, which is not a bad/good thing per se. I tend to like it, if done well.
This book is not for graduate students without a serious background in decision theory, and Bayesian theory. It's definitely not an introduction for graduate students. Why? Because the whole book reads as a compendium of examples taken from published research by many authors, where only some clues are given and most claims are just stated. This can be a bit frustrating for those who like to prove everything they come across, since it would take much more than 6 months to scavenge over most of the references. Therefore, it's seems ironic that to read a theoretical book, one needs to take practical/pragmatic approach.
This aspect could be improved if most of the references to tables and exercises were correct. For example: page 81(section 2.5.4) of the paperback edition, sends the reader to exercise 2.36 for an example showing that bayes estimators are not invariant to bijective(1-to-1) transformations. Checking that exercise, we see that it's not that, since this belongs to section 2.4.3. So, searching on the right section of exercises we find that it's 2.46 the correct exercise. There are several examples where references to tables and images are incorrect. This will make studying by this book much more difficult than needed, and getting to the point where you're not sure anymore if you're reasoning correctly.
Another nature of typos, and this time, much more serious is given in example 4.1.3. The definition of the likelihood and pmf has two typos in each that prevent you from understanding it at all, if you're not yourself familiarised with the example. Mind you, that's it's been more than 10 years, and the list of typos available at the author's web page lacks both of these I'm telling you about and much more. In this case, I had to search the reference given - which is a set of 150 pages of lecture notes written in the 80's, i.e. a typewriter was used - just to find the correct definitions... I simply don't have the time for such a task every time I think there's a mistake. There needs to be some trust that what's written is correctly written, otherwise the book mines that trust, preventing me from using it as a reference. All of this in just 4 chapters, in an 11 chapters book.
If you happen to have the solutions manual available to you, then you'll see just how worse this torrent of typos can be. And the sol. manual has been 'revised extensively'...
Honestly, this reminds me of a book edited by someone prone to dyslexic fits, who is writing for his peers already very familiar with the subject, and who've got other books, as a reference and as an introduction... This seems a perfect example of how reputation precedes quality in some cases, and the editors can be much more lenient.
I hope he does(did) a better job in his future(past) books.
Most helpful customer reviews on Amazon.com
However, for those who want to apply bayesian statistics to a problem in their own research area, there are likely better books. The author uses many concepts before introducing them. In many cases, the introduction of a concept is so brief as to only serve as a reminder for those who already know the topic well. I have taken several graduate courses in statistics and I have studied most of the topics listed in the table of contents, yet I find this book difficult to follow.
I feel reviews are often colored by the (often unknown) background of the reviewer, so I'm including a little of my background: I have a phd in computer science and my thesis topic was computer vision. I am now working on machine learning problems and when I bought this book I felt a stronger background in bayesian statistics would help me.