Draft:BUGS language

Submission declined on 3 August 2026 by MSK (talk). This draft appears to contain text generated by a large language model (such as ChatGPT). You cannot use LLMs to generate article content. LLM-generated pages with certain obvious signs of being machine generated may be deleted without notice. Instead, only summarize in your own words a range of independent, reliable, published sources that discuss the subject. See the advice page on large language models for more information. If you would like to continue working on the submission, click on the "Edit" tab at the top of the window. If you have not resolved the issues listed above, your draft will be declined again and potentially deleted. If you need extra help, please ask us a question at the AfC Help Desk or get live help from experienced editors. Please do not remove reviewer comments or this notice until the submission is accepted. Where to get help If you need help editing or submitting your draft, please ask us a question at the AfC Help Desk or get live help from experienced editors. These venues are only for help with editing and the submission process, not to get reviews. If you need feedback on your draft, or if the review is taking a lot of time, you can try asking for help on the talk page of a relevant WikiProject. Some WikiProjects are more active than others so a speedy reply is not guaranteed. How to improve a draft Wikipedia:Contributing to Wikipedia – a basic overview on how to edit Wikipedia. Help:Wikitext – how to use the markup Help:Referencing for beginners – how to include references Wikipedia:Article development – how to develop your article Wikipedia:Writing better articles – how to improve your article Wikipedia:Verifiability – make sure your article includes reliable third-party sources You can also browse Wikipedia:Featured articles and Wikipedia:Good articles to find examples of Wikipedia's best writing on topics similar to your proposed article. Improving your odds of a speedy review To improve your odds of a faster review, tag your draft with relevant WikiProject tags using the button below. This will let reviewers know a new draft has been submitted in their area of interest. For instance, if you wrote about a female astronomer, you would want to add the Biography, Astronomy, and Women scientists tags. Add tags to your draft Editor resources Easy tools: Citation bot (help) | Advanced: Fix bare URLs Declined by MSK 18 days ago. Last edited by MSK 18 days ago. Reviewer: Inform author. Resubmit Please note that if the issues are not fixed, the draft will be declined again.

BUGS (Bayesian inference Using Gibbs Sampling) is a declarative programming language and associated software framework for specifying and fitting complex Bayesian statistical models via Markov chain Monte Carlo (MCMC) methods. Conceived in 1989 at the MRC Biostatistics Unit, University of Cambridge, BUGS has been influential for over 30 years in enabling routine use of Bayesian methods across many scientific disciplines.

The BUGS language allows users to specify graphical models in a declarative style: the user describes the probabilistic structure of a model and the software automatically selects appropriate MCMC algorithms — primarily Gibbs sampling — to estimate the posterior distribution of model parameters.

The language is built around two core concepts:

• A declarative model specification, in which the user describes conditional relationships among variables rather than writing procedural simulation code.
• Automatic MCMC, in which the software selects updating algorithms based on the structure of the model, without requiring the user to implement samplers manually.

The BUGS project began in 1989 at the MRC Biostatistics Unit in Cambridge, UK.^[1]. The first implementation, ClassicBUGS, was described by Spiegelhalter et al. in 1996 ^[2]. Development subsequently produced WinBUGS, released in 1997 ^[3], which introduced a graphical interface including a "Doodle Editor" for constructing models visually. OpenBUGS, an open-source implementation, followed in 2005. The most recent major implementation, MultiBUGS, adds support for parallel computation ^[4] The BUGS language and its use for statistical modelling is described in detail in a dedicated textbook.^[5]

The original implementation of the BUGS language, available for Unix systems. Described by Spiegelhalter et al. (1996).

Released in 1997 by the BUGS Project — a team of British researchers at the MRC Biostatistics Unit, Cambridge, and Imperial College School of Medicine, London — WinBUGS was the first widely adopted implementation. It introduced graphical model specification via "Doodles" and ran under Microsoft Windows. The final version, 1.4.3, was released in August 2007 and is no longer under active development.

OpenBUGS is the open-source successor to WinBUGS, initially released in 2005 and developed by the OpenBUGS Foundation. It runs on Windows, Linux, and macOS (via Wine), and is licensed under the GNU General Public License. The stable release is version 3.2.3 (2014); it is no longer actively developed.

MultiBUGS extends the OpenBUGS codebase with support for parallel computation, enabling faster Bayesian inference on modern multi-core hardware. It automatically parallelises the MCMC algorithm without requiring users to write parallel code. It is hosted on GitHub and described in Goudie et al. (2020).^[4]

BUGS model specifications are written in a declarative style. Stochastic relationships are expressed using the ~ symbol (indicating a probability distribution), while deterministic relationships use <-. A simple example:

model {
  # Likelihood
  for (i in 1:N) {
    y[i] ~ dnorm(mu, tau)
  }
  # Priors
  mu ~ dnorm(0, 0.001)
  tau ~ dgamma(0.001, 0.001)
  sigma <- 1 / sqrt(tau)
}

Several R packages provide interfaces to BUGS implementations:

• R2WinBUGS – interface to WinBUGS
• R2OpenBUGS – interface to OpenBUGS
• R2jags – interface to JAGS, a BUGS-compatible alternative
• R2MultiBUGS – interface to MultiBUGS

The BUGS project has been highly influential in enabling the routine use of Bayesian methods across many scientific disciplines..^[6] The core implementations (WinBUGS and OpenBUGS) are no longer actively developed, though they remain available and are still used in teaching and legacy research workflows.

The declarative modelling approach pioneered by BUGS has been widely adopted by successor probabilistic programming frameworks. The BUGS language itself continues to be supported through JAGS, which accepts BUGS-syntax model specifications and is actively maintained as a cross-platform alternative ^[7]. Other actively developed successors include:

• Stan – uses gradient-based Hamiltonian Monte Carlo sampling and has a large community of users^[8].
• NIMBLE – adopts and extends the BUGS language, additionally allowing users to write and customise their own sampling algorithms ^[9].
• Turing – a probabilistic programming framework for the Julia language ^[10]

• The BUGS Project – MRC Biostatistics Unit, University of Cambridge
• MultiBUGS
• BUGS mailing list

Category:Bayesian statistics Category:Statistical software Category:Domain-specific programming languages