Doing Bayesian Data Analysis: A Tutorial with R, JAGS, and Stan

Key differences between 2nd and 1st editions

• Period between current and previous editions: 4 years (2014 vs 2010).
• In the Second Edition J. Kruschke presents all new programs in JAGS and Stan.
• New Chapter 3 on R Programming Language, which is used for the development of computer programs for statistics and data analysis.
• Two former separate chapters -- Chapter 7 "Inferring a Binomial Proportion via the Metropolis Algorithm" and Chapter 8 "Inferring Two Binomial Proportions via Gibbs Sampling" -- have been consolidated into a single Chapter 7 "Markov Chain Monte Carlo". This chapter now presents new material on Markov Chain Monte Carlo (MCMC) convergence diagnostic methods.
• Completely new Chapter 8 on Just another Gibbs sampler (JAGS), a program for investigation of Bayesian hierarchical models, written by Martyn Plumme.
• Chapter 9 includes new material on shrinkage in hierarchical models.
• New Chapter 10 "Model Comparison and Hierarchical Modeling" consolidated into a single chapter all the material on model comparison, which was spread across various chapters in the First edition.
• Chapter 10 now contains all the material on model comparison, which was spread across multiple chapters before.
• Chapter 11: new material on sampling distributions used to test hypotheses.
• Chapter 12: new material about the region of practical equivalence (ROPE); Savage-Dickey approximations to the Bayes factor.
• Chapter 13: new section 13.3 "Sequential Testing and the Goal of Precision".
• New Chapter 14 on Stan, an imperative probabilistic programming language.
• Chapter 16: new section 16.3 on metric predicted variable on two groups.
• Chapter 18: new section 18.4 "Variable Selection".
• Chapter 19: new examples on analysis of covariance (ANCOVA).
• Chapter 21 includes examples of robust logistic regression.
• New Chapter 22 "Nominal Predicted Variable" covers:
• Softmax regression (a form of multinomial logistic regression)
• Conditional (fixed-effects) logistic regression
• Implementation in JAGS (Just Another Gibbs Sampler)
• Models generalizations and variations
• Chapter 23 has examples showing single-group and two-group analyses.
• Chapter 25: new section 25.4 "Censored Data in JAGS".