.png){kind=icon}
.png){kind=icon}
Return
Simulation-Based Bayesian Analysis
.png){kind=icon}
OA
AI
DOI：10.1146/annurev-statistics-122121-040905.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
I consider the development of Markov chain Monte Carlo (MCMC) methods, from late-1980s Gibbs sampling to present-day gradient-based methods and piecewise-deterministic Markov processes. In parallel, I show how these ideas have been implemented in successive generations of statistical software for Bayesian inference. These software packages have been instrumental in popularizing applied Bayesian modeling across a wide variety of scientific domains. They provide an invaluable service to applied statisticians in hiding the complexities of MCMC from the user while providing a convenient modeling language and tools to summarize the output from a Bayesian model. As research into newMCMCmethods remains very active, it is likely that future generations of software will incorporate new methods to improve the user experience.
Keywords:
Bayesian computation
Bayesian inference
Gibbs sampling
graphical model
statistical software
MCMC
INLA
BUGS
Stan
JAGS
PDMPs
Journal
IF:
8.7
Papers:
211
Citations:
2.4K