Abstract: Direct sampling techniques for generating multivariate variables are often practically infeasible for Bayesian inference, except for simple models. This chapter introduces the Gibbs sampling method also known as the Gibbs sampler. The Gibbs sampler has become the most popular computational method for Bayesian inference. Technically, the Gibbs sampler can be viewed as a special method for overcoming the curse of dimensionality via conditioning. The data augmentation (DA) algorithm can be viewed as a special case of the Gibbs sampler, the two-step Gibbs sampler. It is also viewed as the stochastic version of the EM algorithm. Controlled Vocabulary Terms Bayesian inference; Gibbs sampling
Publication Year: 2010
Publication Date: 2010-07-07
Language: en
Type: other
Indexed In: ['crossref']
Access and Citation
Cited By Count: 3
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot