A Tutorial on Markov Chain Monte-Carlo and Bayesian Modeling
Preprint
- 3 January 2021
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
This tutorial provides an introduction to Bayesian modeling and Markov Chain Monte-Carlo (MCMC) algorithms including the Metropolis-Hastings, Gibbs sampling and Hamiltonian Monte-Carlo algorithms. We discuss some of the challenges associated with running MCMC including the important question of determining when convergence to stationarity has been achieved. Several applications of Bayesian modeling are also provided including the MRP approach to modeling election outcomes, topic modeling in machine learning, and large-scale optimization and code breaking. We also discuss the important problems of Bayesian model checking and selection and provide an introduction to empirical Bayesian models. In the appendices we briefly discuss: (i) other problems in Bayesian statistics including Bayesian approaches to constructing confidence intervals, hypothesis testing and decision theory, and (ii) the EM algorithm which relates to the block Gibbs sampling algorithm.Keywords
This publication has 24 references indexed in Scilit:
- Practical Bayesian model evaluation using leave-one-out cross-validation and WAICStatistics and Computing, 2016
- Computer Age Statistical Inference2016
- The ASA Statement on p -Values: Context, Process, and PurposeThe American Statistician, 2016
- Bayesian Reasoning and Machine Learning2012
- A tutorial on Bayesian nonparametric modelsJournal of Mathematical Psychology, 2012
- Introducing Monte Carlo Methods with R2010
- Monte Carlo Statistical Methods2004
- Explaining the Gibbs SamplerThe American Statistician, 1992
- On the Foundations of Statistical InferenceJournal of the American Statistical Association, 1962
- Equation of State Calculations by Fast Computing MachinesThe Journal of Chemical Physics, 1953