Movatterモバイル変換

jSDM 0.2.7

• Changing maintainer to Ghislain Vieilledentghislain.vieilledent@cirad.fr.

jSDM 0.2.6

• From 0.2.2 to 0.2.6, there are only minor corrections to pass checkson CRAN.

jSDM 0.2.2

• New functionjSDM_gaussianfor fitting joint species distribution models from continuous Gaussiandata, including an overdispersion parameter.
• Use of the R packageterra instead ofraster andsp, which are depreciated, in thevignetteEstimationof Madagascar’s plant biodiversity.

jSDM 0.2.1

• Add the possibility to consider only significant correlations in theget_residual_corandplot_residual_corfunctions.
• Documentation corrections

jSDM 0.2.0

• New functionjSDM_binomial_probit_sp_constrainedwhich aims to improve the convergence of latent variable models fittingby selecting the species constrained to have positive values of factorloadings\(\lambda\) and new vignetteBernoulliprobit regression with selected constrained species to illustrateits use.
• New vignetteEstimationof Madagascar’s plant biodiversity available.

jSDM 0.1.2

• Add the possibility of considering an additional hierarchical levelin the Bayesian models of thejSDM_binomial_probit,jSDM_binomial_logitandjSDM_poisson_logfunctions to take into account interactions between species-specifictraits and the environment in estimating species effects.
• New vignetteBernoulliprobit regression including species traits available.
• Separate the drawing of species effects beta and factor loadinglambda in the functionsjSDM_binomial_probit_block andjSDM_binomial_probit_block_long_format renamedjSDM_binomial_probitandjSDM_binomial_probit_long_format.
• New functionplot_associationsto plot species-species associations.

jSDM 0.1.1

• Use ofroxygen2 for documentation and NAMESPACE.
• RenamejSDM_binomial_probit_block the functionjSDM_probit_block.
• New functionjSDM_binomial_probit_block_long_format forfitting joint species distribution models from presence-absence data inlong format able to handle missing observations, multiple visits atsites and to integer species traits as explanatory variables.
  
• New functionjSDM_poisson_logfor fitting joint species distribution models from abundance datainspired by Hui and Francis K. C. 2016Methods in Ecology andEvolution (doi:10.1111/2041-210X.12514).
• New functionjSDM_binomial_logitfor fitting joint species distribution models from presence-absence dataat multiple-visited sites using a bayesian inference method inspired byAlbert, James H. and Chib Siddhartha 1993Journal of the AmericanStatistical Association (doi:10.1080/01621459.1993.10476321).
• Functions to fit models in which site effects are included as fixedeffects, as random effects or not included and with or without latentvariables.
• New functionget_enviro_corto extract covariances and correlations due to shared environmentalresponses.
• CompletingjSDM-packagedocumentation
• Add datasets (mosquitos,fungi,eucalypts,birds,mites,aravo).
• Seven new vignettes (Bayesianinference methods,Poissonlog-linear regression,Bernoulliprobit regression,Bernoulliprobit regression with missing data and species traits,Binomiallogistic regression,RunningjSDM in parallel,ComparingSDMs and JSDMs andComparisonjSDM-Hmsc) are available.
• Completing and correcting the vignetteComparisonjSDM-boral.
• Adding Code of conduct and Contributing sections.
• New package website available on GitHub:https://ecology.ghislainv.fr/jSDM/.

jSDM 0.1.0

• First version of the jSDM R package
• Use of Rcpp and C++ code for Gibbs sampling
• Use of GSL (RcppGSL) for random draws
• Use of Armadillo (RcppArmadillo) for vector and matrixoperations
• Functions to fit models from Warton et al. 2014Trends inEcology and Evolution (doi:10.1016/j.tree.2015.09.007).
• We usepkgdown to build package website.
• Package website available on GitHub:https://ecology.ghislainv.fr/jSDM/.