Any suggestions for a good source to learn MCMC methods?
Asked
Active
Viewed 1.5k times
34
-
3Related question: [good summaries (reviews, books) on various applications of Markov chain Monte Carlo (MCMC)](http://stats.stackexchange.com/q/32325/22228) – Silverfish Jan 16 '15 at 12:20
7 Answers
16
For online tutorials, there are
- A tutorial in MCMC, by Sahut (2000)
- Tutorial on Markov Chain Monte Carlo, by Hanson (2000)
- Markov Chain Monte Carlo for Computer Vision, by Zhu et al. (2005)
- Introduction to Markov Chain Monte Carlo simulations and their statistical analysis, by Berg (2004).
- A Tutorial on Markov Chain Monte-Carlo and Bayesian Modeling by Martin B. Haugh (2021).
Practical Markov Chain Monte Carlo, by Geyer (Stat. Science, 1992), is also a good starting point, and you can look at the MCMCpack or mcmc R packages for illustrations.
9
I haven't read it (yet), but if you're into R, there is Christian P. Robert's and George Casella's book: Introducing Monte Carlo Methods with R (Use R)
I know of it from following his (very good) blog
Xi'an
- 90,397
- 9
- 157
- 575
Tal Galili
- 19,935
- 32
- 133
- 195
-
This book doesn't go in depth into MCMC. It actually have a page on it and skip MCMC theory in its entirety to go into Metropolist hashing. – Anthony Doan Apr 19 '17 at 05:57
-
While you are 100% entitled to your own opinion on our book, I beg to disagree with the notion that we do not go in depth into MCMC there. Judging from the question I do not think the OP was asking for the deep theory of MCMC algorithms (which is somehow covered in our earlier book). – Xi'an Nov 01 '17 at 11:27
6
Gilks W.R., Richardson S., Spiegelhalter D.J. Markov Chain Monte Carlo in Practice. Chapman & Hall/CRC, 1996.
A relative oldie now, but still a goodie.
onestop
- 16,816
- 2
- 53
- 83
6
Chapter 4, 'Inference from simulations and monitoring convergence' by Gelman and Shirley, is available online.
David LeBauer
- 7,060
- 6
- 44
- 89
-
1Looks set to kick Gilks, Richardson & Spiegelhalter (1996) into the long grass when that comes it in May. – onestop Jan 03 '11 at 09:35
4
Another classic position (as accompanied to already mentioned Introducing Monte Carlo Methods with R):
Monte Carlo Statistical Methods by Robert and Casella (2004)
in the Use R! series there is also:
Introduction to Probability Simulation and Gibbs Sampling with R by Suess and Trumbo (2010)
Tim
- 108,699
- 20
- 212
- 390
4
-- a more recently updated book than Gilks, Richardson & Spiegelhalter. I haven't read it myself, but it was well reviewed in Technometrics in 2008, and the first edition also got a good review in The Statistician back in 1998.
0
The text I have found most accessible is Bayesian Cognitive Modeling: A Practical Course. Very clear exposition. The book has great examples in BUGS, and they have been ported to Stan on its github examples page.
stewart
- 1