Skip to content

Handbook of Markov Chain Monte Carlo

Galin Jones, Steve Brooks, Xiao-Li Meng and I edited a handbook of Markov Chain Monte Carlo that has just been published. My chapter (with Kenny Shirley) is here, and it begins like this:

Convergence of Markov chain simulations can be monitored by measuring the diffusion and mixing of multiple independently-simulated chains, but different levels of convergence are appropriate for different goals. When considering inference from stochastic simulation, we need to separate two tasks: (1) inference about parameters and functions of parameters based on broad characteristics of their distribution, and (2) more precise computation of expectations and other functions of probability distributions. For the first task, there is a natural limit to precision beyond which additional simulations add essentially nothing; for the second task, the appropriate precision must be decided from external considerations. We illustrate with an example from our current research, a hierarchical model of trends in opinions on the death penalty in U.S. states.

To read all the other chapters, you’ll have to buy the book!


  1. Manoel Galdino says:

    I'm considering to buy it. However, I would like more information (I can't 'see inside the book' at Amazon).

    What background is required to read this book?
    Do I need to have previous knowledge of MCMC? Is it enough to have been using WinBugs?

    Does it have program code in the application part of the book? If yes, in which programming languages (R, C, C++, WinBugs/Jags, Matlab etc.).

    Could I have access to the table of contents of the book?


  2. Bob Carpenter says:

    To look at the contents (or pay the full $100 for it), check out the book's home page from the publisher (not the abandoned home page):

    As with many of these things, you'll find various chapters on various authors home pages. For instance, Andrew and Kenny's contribution is linked in the main blog post, and I'll let you search for others online (for instance, Radford Neal's great overview of Hamiltonian Monte Carlo, which indeed comes with R implementations).

    Unfortunately for those of us on a budget, statisticians aren't as prone as computer scientists to include PDFs of all their writings on their home pages.

  3. Manoel Galdino says:

    Thanks for the links. As I expected, it sounds interesting. I'll probably buy it. Actually, I think I have all books writen by Gelman I'm pretty glad with all of them. I just have to decidee if it's better a e-book or the traditional printed version.