https://github.com/betanalpha/mcmc_diagnostics

Markov chain Monte Carlo general, and Hamiltonian Monte Carlo specific, diagnostics for Stan
https://github.com/betanalpha/mcmc_diagnostics

Last synced: 1 day ago
JSON representation

Markov chain Monte Carlo general, and Hamiltonian Monte Carlo specific, diagnostics for Stan

• Host: GitHub
• URL: https://github.com/betanalpha/mcmc_diagnostics
• Owner: betanalpha
• License: bsd-3-clause
• Created: 2022-11-26T15:32:16.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2024-09-13T19:43:29.000Z (2 months ago)
• Last Synced: 2024-09-14T10:42:47.356Z (2 months ago)
• Language: HTML
• Size: 56.8 MB
• Stars: 73
• Watchers: 9
• Forks: 6
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
A suite of analysis and diagnostics tools in `R` and `python` for working with

Markov chain Monte Carlo generally and Hamiltonian Monte Carlo specifically.

The suite includes functions for interfacing with `RStan`, `PyStan2`, and

`PyStan3` and notebooks demonstrating their use.

These tools can also be interfaced with any Hamiltonian Monte Carlo code by

implementing appropriate `extract_expectands`, `extract_hmc_diagnostics`, and

`plot_inv_metric` functions.

Recommendations for code optimization are welcomed and appreciated.

### Acknowledgements {-}

I thank Sean Talts and Dan Waxman for Python code improvements.  Raoul Kima

originally suggested separating divergent transitions by numerical trajectory

length.