Stan is a state-of-the-art platform for statistical modeling and high-performance statistical computation.Thousands of users rely on Stan for statistical modeling, data analysis, and prediction in the social, biological, and physical sciences, engineering, and business.

Users specify log density functions in Stan's probabilisticprogramming language and get:

• full Bayesian statistical inference with MCMC sampling (NUTS, HMC)

• approximate Bayesian inference with variational inference (ADVI, Pathfinder)

• penalized maximum likelihood estimation with optimization (L-BFGS)

Stan'smath library provides differentiable probability functions & linear algebra (C++ autodiff).Additional R packages provideeasy formula syntax to specify linear and generalized linear hierarchical models,posterior visualization, andleave-one-out cross-validation.

Stan interfaces with the most popular data analysis languages (R, Python, shell, MATLAB, Julia, Stata) and runs on all major platforms (Linux, Mac, Windows).To get started using Stan begin with theInstallation andDocumentation pages.

Stan is an active and open developer community. Thehelp-wanted andgood-first-issue labels in our repositories try to highlight good places to get started, and we're happy to help more on ourforums or Slack.

We have projects in C++, Python, R, OCaml, and more.If you want to help build future versions of Stan, we want to help you get started.

We appreciate citations for the Stan software because it lets us find out what people have been doing with Stan and motivate further grant funding.SeeHow to Cite Stan for more details.

Stan is freedom-respecting, open-source software (new BSD core, some interfaces GPLv3). Stan is associated with NumFOCUS, a 501(c)(3) nonprofit supporting open code and reproducible science, through which you canhelp support Stan.

Repositories

Most used topics