CT/RJ-Mix: Transdimensional MCMC for Gaussian mixtures

This is the companion web site for the paper

Olivier Cappé, Christian Robert and Tobias Rydén. Reversible jump, birth-and-death and more general continuous time Markov chain Monte Carlo samplers. Journal of the Royal Statistical Society: Series B (Statistical Methodology), Volume 65, Issue 3, pages 679-700, 2003.

The purpose of the software available from this page is to implement transdimensional Markov Chain Monte Carlo (MCMC) for inference in (scalar) Gaussian mixture models, with unknown number of components. Two methods are implemented: Reversible Jump (RJ) MCMC for rj_mix and Continuous Time (CT) for ct_mix The software is C code which is distributed in source form (please read the manual for further details): manual.pdf Manual in PDF format ctrj_mix.zip Zip compressed archive with everything ctrj_mix.tgz Gzip compressed Unix tar file with everything

The current version of the software is 3.6 (the current version and time stamp are printed on each page of the manual, each individual file has its own version number which may differ)

You can find a preprint version of the JRSSB paper here (gzip-compressed ps file) (note: this is not the published version and is provided for your personal use only, please read the copyright notice in case of doubt).

@misc{ctrj_mix,
  author	= {O. Capp\'{e} and C. Robert and T. Ryd\'{e}n},
  title		= {{CT/RJ-Mix}: {T}ransdimensional {MCMC} for {G}aussian mixtures (available as {C} source code)},
  url		= {http://www.tsi.enst.fr/~cappe/ctrj_mix/},
  month		= dec,
  year		= {2003},
}