Bayesian Econometrics

This is an excellent text for a graduate course where someone is providing guidance and supplementary information. As a standalone text, the reader will lack proofs, but will be directed to many available supplements for additional detail.Primary topics include an overview of standard Bayesian theory, as well as many different likelihood functions, marginal distributions, and conditional distributions. He covers model comparison using posterior odds ratios and Bayes factors, posterior predictive p-values, the Savage Dickey density ratio (for nested models), and posterior predictive distributions / marginal likelihoods (including Chib's method and Gelfand-Dey methods for calculation). He covers models with known and unknown heteroskedasticity, autocorrelated errors, ARCH, and GARCH. He also touches on pooled models i.e. individual effects and random effects models, as well as local and general state space models with latent variables. This leads to discussion of nonlinear models, including Tobit, Probit, and Logit. He briefly explains nonparametric models and mixture of Normals models.Several different priors are covered, including conjugate Normal-Gamma priors, independent Normal-Gamma priors, Normal-Wishart priors, diffuse prior settings, vague (non-informative) priors, and more.The author covers several technique for distributions without analytical solutions, including Monte Carlo integration, inverse-distribution method, importance sampling, acceptance sampling, Metropolis-Hastings, and Markov Chain Monte Carlo methods like Gibbs sampling, Gibbs with data augmentation, and Metropolis-in-Gibbs.At the end, the author provides sources for other concepts, including Bayesian model averaging, Markov Chain Monte Carlo Model Composition, Griddy-Gibbs sampling, adaptive rejection sampling, the Laplace approximation, the Tierney-Kadane approximation, reference priors (Jeffreys'), information criterion (AIC/BIC, etc.), training sample priors, identification, simultaneous equation models (like Bayesian Vector Autoregression and Seemingly Unrelated Regressions), regime switching models (like Threshold Autoregression models, Smooth Transition Autoregressive models, and Markov Switching models), Treatment Effects models, and spline models.

Was a novice at Bayesian econometrics and the book, as well as the accompanying website proved very useful. The book is simple to follow yet includes various applications.

Very clear exposition of Bayesian econometrics. A wide range of topics with description of computational algorithms available for download on the book's website.

The best bayes econ there is. In my opinion. Good balance of prose and math.

It is a good book, original on its own, since it is among the only to introduce econometrics from a bayesian perspective. The explanations are clear, in that sense. It is meant to be for people with little or no prior exposure to statistics, but I believe you may suffer a bit if you approach it from that point.The main problem is common to most econometric books: the teaching of the units is not coupled to any software. That is a teaching choice of the author, of course, but if you are considering to learn bayesian (applied) statistics, you definitely would like to learn it in a programming environment.

the cover page is abrasive, which should be new. This is my first time to get such a book with low quality.

This could have been a great book. But, it is lost in the wilderness of its own formulations. It lacks focus.