The MRC Biostatistics Unit understands the importance of creating accessible software for putting new statistical methods into practice. Many BSU scientists are involved in such projects which are typically made freely available and open-source. Some noteable examples are detailed on this page and our website also keeps a lightly managed archive of code produced in the unit here.

The BUGS Project

BUGS is a language and various software packages for Bayesian inference Using Gibbs Sampling, conceived and initially developed at the BSU. Throughout its 20-year life span, BUGS has been highly influential in enabling the routine use of Bayesian methods in many areas. You can find out more about the software at the BUGS Project pages; if you are using MultiBUGS you might want to investigate its stand-alone website.

Bayesian Approaches to Clinical Trials and Health-Care Evaluation

Information and supporting documentation for this book can be found at the following page.

R packages

In recent years R has become a popular language for software concerning statistical methods. In this subsection we list some notable BSU based packages.

Packages on CRAN with open source contributing

• bcrm: Bayesian continual reassessment method (CRM) designs for Phase I dose-finding trials.
• flexsurv: flexible parametric models for time-to-event data, including the Royston-Parmar spline model, generalized gamma and generalized F.
• coloc: Colocalisation tests of two genetic traits
• msm: multi-state modelling: Developed by Christopher Jackson msm implements general Markov and hidden Markov models. Details can be found in Jackson (Journal of Statistical Software, 2011).
• BASiCS: Bayesian Analysis of Single-Cell Sequencing data (on Bioconductor rather than CRAN)

Packages on CRAN

• PReMiuM: for Dirichlet process Bayesian clustering, or profile regression.
• denstrip: for density strips and other plots for compactly illustrating distributions.
• ecoreg: for ecological regression using aggregate and individual data.
• mreg: Likelihood estimation for a longitudinal negative binomial regression model with missing outcomes.
• DeLorean: For the analysis of single cell transcriptomic data with uncertainty in the temporal dimension (github page).

Open source contributing

• GUESSFM: R package for fine mapping genetic associations in dense or imputed GWAS genotype data
• R2BGLiMS: An R interface to BGLiMS (Bayesian Generalised Linear Model Selection); a Java package for fitting survival and logistic Bayesian models under Reversible Jump model selection.
• ShrinkNet: Gene network reconstruction using global-local shrinkage priors

Other Code listings associated with the BSU

• Chris Wallace (Statistical Genomics) has a software listing available here.
• The Burgess group (Mendelian Randomization) maintain their own code listing here.
• The github account dose-finding provides repositories supporting some of the work within the DART theme.