[R-pkgs] dclone 1.3-0

Peter Solymos solymos at ualberta.ca
Mon Jan 3 18:05:20 CET 2011


Dear R Community,

I am happy to introduce the latest version 1.3-0 of the 'dclone' R package.

The package provides low level functions for implementing maximum
likelihood estimating procedures for complex models using data cloning
and Bayesian Markov chain Monte Carlo methods with support for JAGS,
WinBUGS and OpenBUGS.

Data cloning is a global optimization approach and a variant of
simulated annealing which exploits Bayesian MCMC tools to get maximum
likelihood point estimates and corresponding standard errors (see Lele
et al. 2007, Ecology Letters, 10:551-563).

The implementation used in the 'dclone' package is described in the
recent paper: Solymos, P. 2010. dclone: Data Cloning in R. The R
Journal, 2(2):29-37. URL:
http://journal.r-project.org/archive/2010-2/RJournal_2010-2_Solymos.pdf

The current release of 'dclone' supports parallel computations via the
'snow' package.

Have fun,

Peter

Peter Solymos
Alberta Biodiversity Monitoring Institute
and Boreal Avian Modelling project
Department of Biological Sciences
CW 405, Biological Sciences Bldg
University of Alberta
Edmonton, Alberta, T6G 2E9, Canada
Phone: 780.492.8534
Fax: 780.492.7635
email <- paste("solymos", "ualberta.ca", sep = "@")
http://www.abmi.ca
http://www.borealbirds.ca
http://sites.google.com/site/psolymos

--

Main functions in the 'dclone' package include:

* dclone, dcdim: cloning R objects in various ways.

* jags.fit, bugs.fit: conveniently fit BUGS models. (jags.parfit fits
chains on parallel
workers for JAGS.)

* dc.fit: iterative model fitting by the data cloning algorithm.
(dc.parfit is the parallelized
version.)

* dctable, dcdiag: helps evaluating data cloning convergence by
descriptive statistics and diagnostic tools. (These are based on e.g.
chisq.diag and lambdamax.diag.)

* coef.mcmc.list, confint.mcmc.list.dc, dcsd.mcmc.list,
quantile.mcmc.list, vcov.mcmc.list.dc, mcmcapply: convenient functions
for mcmc.list objects.

* write.jags.model, clean.jags.model, custommodel: convenient
functions for handling
BUGS models.



More information about the R-packages mailing list