- Hardcover: 222 pages
- Publisher: Cambridge University Press; 1 edition (October 8, 2007)
- Language: English
- ISBN-10: 0521858712
- ISBN-13: 978-0521858717
- Product Dimensions: 7 x 0.6 x 10 inches
- Shipping Weight: 1.3 pounds (View shipping rates and policies)
- Average Customer Review: 3 customer reviews
- Amazon Best Sellers Rank: #2,916,779 in Books (See Top 100 in Books)
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.
Introduction to Bayesian Econometrics 1st Edition
Use the Amazon App to scan ISBNs and compare prices.
The Amazon Book Review
Author interviews, book reviews, editors picks, and more. Read it now
Customers who viewed this item also viewed
"This book provides an excellent introduction to Bayesian econometrics and statistics with many references to the recent literature that will be very helpful for students and others who have a good background in the calculus. Basic Bayesian estimation, testing, prediction and decision techniques are clearly explained with applications to a broad range of models and many computed examples are provided to illustrate general principles. Classical and modern computing techniques are clearly explained and applied to solve central inference problems. Also, references to downloadable computer algorithms are included in this impressive book." - Arnold Zellner, Graduate School of Business, University of Chicago
"This concise book provides an excellent introduction to modern, simulation-based Bayesian econometrics. It covers the theoretical underpinnings, the MCMC algorithm, and a large number of important econometric applications in an accessible yet rigorous manner. I highly recommend Greenberg's book as a Ph.D.-level textbook and as a source of reference for researchers entering the field." - Rainer Winkelmann, University of Zurich
"Professor Greenberg has assembled a tremendously valuable resource for anyone who wants to learn more about the Bayesian world. The book begins at an introductory level that should be accessible to a wide range of readers. Professor Greenberg then builds on these fundamental ideas to help the reader develop an in-depth understanding of the major concepts and methods used in modern Bayesian econometrics. The explanations are very clearly written, and the content is supported with many detailed examples and real-data applications." - Douglas J. Miller, University of Missouri - Columbia
"In Introduction to Bayesian Econometrics, Greenberg skillfully guides us through the fundamentals of Bayesian inference, provides a detailed review of methods for posterior simulation and carefully illustrates the use of such methods for fitting a wide array of popular micro-econometric and time series models. The writing style is accessible and lucid, the coverage is comprehensive, and the associated web site provides data and computer code to clearly illustrate how modern Bayesian methods are implemented in practice. This text is a must-have for the Bayesian and will appeal to statisticians/econometricians of all persuasions." - Justin L. Tobias, Iowa State University
This concise textbook is an introduction to econometrics at the graduate or advanced undergraduate level. It differs from other books in econometrics in its use of the Bayesian approach to statistics. This approach, in contrast to the frequentist approach to statistics, makes explicit use of prior information and is based on the subjective view of probability.
Top customer reviews
There was a problem filtering reviews right now. Please try again later.
I am a former mathematician now training to be a political scientist. The statistics I learned before last year turned me off. What I now know as "frequentist" (or "likelihoodist") statistics seemed like a patchwork of techniques and estimators, a menagerie of coefficients and test statistics. This left me mostly uninterested in leveraging my math skills for doing statistics in political science.
Then I took Ed's class. The book lays it all out. His course was good, but the book made statistics seem almost simple. More accurately, Bayesian methods provide a more unified way of approaching statistical inference.
Many books on Bayesian methods (Carlin and Lewis, Gelfand et al, Press, Gill, others) get too far down into the minutiae of doing Bayesian inference to make clear the overall themes to someone who hasn't worked with Bayesian methods. Ed starts from the beginning, discussing some of the history of statistics and then building from scratch a notion of probability. Specifically, he goes through how frequentists and Bayesians define probability differently, how the different definitions are equivalent in some ways, and how the differences lead to the very different ways of drawing conclusions about the world.
Part I of the book lays out the "Fundamentals of Bayesian Inference," including how to make inferences from posterior distributions, choosing prior distributions, and analytic solutions for a few cases where one can "do" Bayesian stats without a computer.
Part II discusses "Simulation," the essential application of computers that has made Bayesian inference possible only in the last 20 years. Ed explains how classic simulation works, then spends a chapter giving a basic understanding of Markov chains before diving headfirst into the workhorses of MCMC: the Gibbs sampler and the Metropolis-Hastings algorithm. Examples give pseudo-code that is detailed enough so that one can readily turn the math into working code using your language of choice, such as R ([...]
Part III describes specific applications and addresses solutions to problems unique to each model. Here he leverages the modular but unified approach Bayesian stats allows for fitting models by building up more complicated models out of simpler models.
For the class I took, we did all of the exercises in the first two parts and then we wrote a paper using Bayesian methods. A student or researcher who has some experience with Maximum likelihood techniques should be able to read this book, work through the exercises, and then be able to use them for some of the more common models used today. Then, one should go further and read books or articles diving deeply into the esoterics of a particular model. However, this book is the best introduction I have seen for Bayesian methods.
Addendum: there is no errata given at his website even though he states in the intro there is - and this book is full of them - buyer beware!