Performs reversible-jump Markov chain Monte Carlo (Green, 1995) <doi:10.2307/2337340>, specifically the restriction introduced by Barker & Link (2013) <doi:10.1080/00031305.2013.791644>. By utilising a 'universal parameter' space, RJMCMC is treated as a Gibbs sampling problem. Previously-calculated posterior distributions are used to quickly estimate posterior model probabilities. Jacobian matrices are found using automatic differentiation. For a detailed description of the package, see Gelling, Schofield & Barker (2019) <doi:10.1111/anzs.12263>.
| Version: | 0.4.5 |
| Depends: | madness, R (≥ 3.2.0) |
| Imports: | utils, coda, mvtnorm |
| Suggests: | FSAdata |
| Published: | 2019-07-09 |
| Author: | Nick Gelling [aut, cre], Matthew R. Schofield [aut], Richard J. Barker [aut] |
| Maintainer: | Nick Gelling <nickcjgelling at gmail.com> |
| License: | GPL-3 |
| NeedsCompilation: | no |
| Materials: | README |
| CRAN checks: | rjmcmc results |
| Reference manual: | rjmcmc.pdf |
| Package source: | rjmcmc_0.4.5.tar.gz |
| Windows binaries: | r-devel: rjmcmc_0.4.5.zip, r-release: rjmcmc_0.4.5.zip, r-oldrel: rjmcmc_0.4.5.zip |
| macOS binaries: | r-release: rjmcmc_0.4.5.tgz, r-oldrel: rjmcmc_0.4.5.tgz |
| Old sources: | rjmcmc archive |
Please use the canonical form https://CRAN.R-project.org/package=rjmcmc to link to this page.