Skip to main content

BUGS (Specific Statistical)

Bayesian analysis

Functionality Background

Licence availability, restrictions &
links to distributor

BUGS offers flexible software for the Bayesian analysis of complex statistical models using Markov chain Monte Carlo (MCMC) methods. It can be tailored to do a wide range of analyses, but its strength lies in Bayesian regression, hierarchical models and spatio-temporal modelling.

A somewhat old introduction to the package is contained in: Lunn, D. J., Thomas, A., Best, N. and Spiegelhalter, D. (2000). "WinBUGS -- a Bayesian modelling framework: concepts, structure, and extensibility." Statistics and Computing 10: 325--337. A more recent and extensive introduction is available in: Lunn, D. J., Jackson, C., Best, N., Thomas, A. and Spiegelhalter, D. (2013). The BUGS Book: a Practical Introduction to Bayesian Analysis. London, Chapman and Hall.

An Excel front-end to BUGS is available: BugsXLA. See P. Woodward (2012). Bayesian Analysis Made Simple: An Excel GUI for WinBUGS. London, Chapman and Hall.

BUGS stands for Bayesian Updating by Gibbs Sampling.

BUGS began as a project in Cambridge at the MRC Biostatistics Laboratory in the late 1980s. It is an open software project. Currently development is focused on OpenBUGS, which can be run as BRUGS within R (see entry on R).

Note that this is public domain software and, while there is reason to be confident in BUGS itself, many add-ins are not tested and validated to commercial standards.

WinBUGs is available at: http://www.mrc-bsu.cam.ac.uk/bugs/winbugs/contents.shtml.

BRUGS may be downloaded at: http://cran.r-project.org/web/packages/BRugs/index.html.

OpenBUGS may be downloaded at: http://www.openbugs.info/w/

The Excel GUI BugsXLA may be downloaded from: http://bugsxla.philwoodward.co.uk/

 

 


Note on Statistical Packages Designed for a Specific Set of Functions:

These packages are designed to provide a limited set of functions, but often more advanced ones than are found in general purpose statistical packages, e.g. time series analysis or Bayesian modelling.

Please share your experiences and examples of how you have used this software by leaving a comment below, to help others choose the right software for their research requirements.