runjags: Interface utilities for MCMC models in Just Another Gibbs Sampler (JAGS) using parallel and distributed computing methods

This package provides high-level interface utilities for JAGS, either running locally (via the rjags package or using multiple cores in parallel) or via distributed computing clusters such as those provided by snow (a Simple Network Of Workstations), Apple Xgrid distributed computing clusters (Mac OS X 10.5-10.7 only), and possibly others via user specified functions. The primary motivation is to facilitate running relatively simple JAGS models to convergence, including evaluating the performance of a model against simulated data, and compatibility with the WinBUGS syntax of model files with data and initial values lists. Runjags interface functions also provide convenience wrappers for automatic control of model convergence assessment and run length diagnostics, calculation of relevant summary statistics, generation of trace and density plots, calculation of DIC, and automatic retrieval of R objects as data and initial values. Running of arbitrary R commands (not involving JAGS) over Xgrid is also supported.

Version: 1.0.0-6
Depends: R (≥ 2.14), coda (≥ 0.16-1), lattice (≥ 0.20-10), parallel
Imports: coda, lattice, parallel, stats, utils
Suggests: rjags
Published: 2013-03-26
Author: Matthew Denwood
Maintainer: Matthew Denwood <matthew.denwood at glasgow.ac.uk>
License: GPL
URL: http://cran.r-project.org/web/packages/runjags/
NeedsCompilation: no
SystemRequirements: jags (see http://mcmc-jags.sourceforge.net)
Citation: runjags citation info
In views: Bayesian
CRAN checks: runjags results

Downloads:

Package source: runjags_1.0.0-6.tar.gz
MacOS X binary: runjags_1.0.0-6.tgz
Windows binary: runjags_1.0.0-6.zip
Reference manual: runjags.pdf
News/ChangeLog:ChangeLog
Old sources: runjags archive

Reverse dependencies:

Reverse depends: bayescount, IsotopeR