The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.

jSDM 0.2.2

• New function jSDM_gaussian for fitting joint species distribution models from continuous Gaussian data, including an overdispersion parameter.
• Use of the R package terra instead of raster and sp, which are depreciated, in the vignette Estimation of Madagascar’s plant biodiversity.

jSDM 0.2.1

• Add the possibility to consider only significant correlations in the get_residual_cor and plot_residual_cor functions.
• Documentation correction

jSDM 0.2.0

• New function jSDM_binomial_probit_sp_constrained which aims to improve the convergence of latent variable models fitting by selecting the species constrained to have positive values of factor loadings \(\lambda\) and new vignette Bernoulli probit regression with selected constrained species to illustrate its use.
• New vignette Estimation of Madagascar’s plant biodiversity available.

jSDM 0.1.2

• Add the possibility of considering an additional hierarchical level in the Bayesian models of the jSDM_binomial_probit, jSDM_binomial_logit and jSDM_poisson_log functions to take into account interactions between species-specific traits and the environment in estimating species effects.
• New vignette Bernoulli probit regression including species traits available.
• Separate the drawing of species effects beta and factor loading lambda in the functions jSDM_binomial_probit_block and jSDM_binomial_probit_block_long_format renamed jSDM_binomial_probit and jSDM_binomial_probit_long_format.
• New function plot_associations to plot species-species associations.

jSDM 0.1.1

• Use of roxygen2 for documentation and NAMESPACE
• Rename jSDM_binomial_probit_block the function jSDM_probit_block.
• New function jSDM_binomial_probit_block_long_format for fitting joint species distribution models from presence-absence data in long format able to handle missing observations, multiple visits at sites and to integer species traits as explanatory variables.
  
• New function jSDM_poisson_log for fitting joint species distribution models from abundance data inspired by Hui and Francis K. C. 2016 Methods in Ecology and Evolution (doi:10.1111/2041-210X.12514).
• New function jSDM_binomial_logit for fitting joint species distribution models from presence-absence data at multiple-visited sites using a bayesian inference method inspired by Albert, James H. and Chib Siddhartha 1993 Journal of the American Statistical Association (doi:10.1080/01621459.1993.10476321).
• Functions to fit models in which site effects are included as fixed effects, as random effects or not included and with or without latent variables.
• New function get_enviro_cor to extract covariances and correlations due to shared environmental responses.
• Complete jSDM-package documentation
• Add datasets (mosquitos, fungi, eucalypts, birds, mites, aravo).
• Seven new vignettes (Bayesian inference methods, Poisson log-linear regression, Bernoulli probit regression, Bernoulli probit regression with missing data and species traits, Binomial logistic regression, Running jSDM in parallel, Comparing SDMs and JSDMs and Comparison jSDM-Hmsc) are available.
• Complete and correct the vignette Comparison jSDM-boral.
• Add Code of conduct and Contributing section
  
• 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 matrix operations
• Functions to fit models from Warton et al. 2014 Trends in Ecology and Evolution (doi:10.1016/j.tree.2015.09.007).
• We use pkgdown to build package website.
• Package website available on GitHub: https://ecology.ghislainv.fr/jSDM/.

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.