<< 1 >>
Rating: 
Summary: Opaque
Review: Bought this book a while ago but just started reading it.This book is unique in that it seems to use the proper proportion of prose, formula and examples and yet somehow manages to be totally opaque to me. Maybe its my frame of mind or something but after going through one chapter I simply cannot force myself to read it any more. The oddest part is that I'm reasonably familiar with the material that I've already read.
Rating: 
Summary: A perfect book for Bayesian Method and Application
Review: Reading it, you could understand more detail about its industrial application. It was very nice guidebook on Bayesian analysis. I thought that this book was able to on your desktop for helping you work or research.
Rating:
Summary: Opaque
Review: The authors provide a graduate level (masters level) text for Bayesian methods. In the first chapter they introduce Fisherian statistical concepts and emphasize the likelihood methods. As Bayesian methods are introduced they often show how similar they are to the Fisherian methods when the prior distributions are diffuse or the sample size is large. The techniques are illustrated through many practical examples. This book is also intended for practitioners of statistical methods who might find use for Bayesian methods. Jimmie Savage's normative theory for decision making is introduced in Chapter 4. Expected utility is the basis for optimum decisions in the Bayesian framework. However, expected utility is not always a sensible procedure and the authors offer modifications. Topics include inference on single parameter and multiparameter distributions, linear models, categorical data analysis and time series methods. In Chapter 6 nonlinear models are considered and techniques for approximating the multidimensional integrals that need to be evaluated for Bayesian posterior and predictive distributions are given. These include numerical and Monte Carlo integration, Laplacian methods, importance sampling and Markov Chain Monte Carlo Methods. A nice list of references is provided in the back of the book.
Rating:
Summary: good graduate level intro to Bayesian methods
Review: The authors provide a graduate level (masters level) text for Bayesian methods. In the first chapter they introduce Fisherian statistical concepts and emphasize the likelihood methods. As Bayesian methods are introduced they often show how similar they are to the Fisherian methods when the prior distributions are diffuse or the sample size is large. The techniques are illustrated through many practical examples. This book is also intended for practitioners of statistical methods who might find use for Bayesian methods. Jimmie Savage's normative theory for decision making is introduced in Chapter 4. Expected utility is the basis for optimum decisions in the Bayesian framework. However, expected utility is not always a sensible procedure and the authors offer modifications. Topics include inference on single parameter and multiparameter distributions, linear models, categorical data analysis and time series methods. In Chapter 6 nonlinear models are considered and techniques for approximating the multidimensional integrals that need to be evaluated for Bayesian posterior and predictive distributions are given. These include numerical and Monte Carlo integration, Laplacian methods, importance sampling and Markov Chain Monte Carlo Methods. A nice list of references is provided in the back of the book.
Rating:
Summary: Demonstrates Application of Bayesian Methods to Problems
Review: This is not a book to teach you the Bayesian approach to statistics. Its purpose is to demonstrate methods of application of Bayesian statistics to various types and classes of statistical problems. This book is very math intense and if you aren't quite comfortable with statistics and mathematical analysis then you will likely have a hard time getting much out of this book. But if you have had a sound undergraduate grounding in these kinds of math skills, you should be able to get a lot out of this book. The book provides worked examples to help clarify its points and there are other problems to work, but the answers are not provided anywhere in the book. There is a nice reference list, an author index, and a separate subject index.
Rating:
Summary: Demonstrates Application of Bayesian Methods to Problems
Review: This is not a book to teach you the Bayesian approach to statistics. Its purpose is to demonstrate methods of application of Bayesian statistics to various types and classes of statistical problems. This book is very math intense and if you aren't quite comfortable with statistics and mathematical analysis then you will likely have a hard time getting much out of this book. But if you have had a sound undergraduate grounding in these kinds of math skills, you should be able to get a lot out of this book. The book provides worked examples to help clarify its points and there are other problems to work, but the answers are not provided anywhere in the book. There is a nice reference list, an author index, and a separate subject index.
<< 1 >>
| 
