Bayesian Error Propagation and Forecast Uncertainty Decomposition R package ErrorTracer version 1.0.2 Provides a full pipeline from regularized or standard regression models (elastic net, linear models, generalized linear models, random forests) to informed Bayesian priors, three-way forecast uncertainty decomposition (parameter / environmental / residual), and forecast shelf life analysis (the quantification of when a forecast becomes uninformative). Designed for ecological and genomic forecasting with climate or environmental covariates. Methods build on Bürkner (2017) <doi:10.18637/jss.v080.i01> for Bayesian regression via 'Stan', Friedman, Hastie, and Tibshirani (2010) <doi:10.18637/jss.v033.i01> for elastic net regularization, Wright and Ziegler (2017) <doi:10.18637/jss.v077.i01> for random forests, and Vehtari, Gelman, and Gabry (2017) <doi:10.1007/s11222-016-9696-4> for leave-one-out cross-validation. Software Depends: R (>= 4.1.0) Imports: brms (>= 2.20.0), ggplot2 (>= 3.4.0), rlang (>= 1.1.0), stats, utils Suggests: loo (>= 2.6.0), bayesplot (>= 1.10.0), scales (>= 1.3.0), tidyr (>= 1.3.0), glmnet (>= 4.1.0), ranger (>= 0.15.0), dplyr (>= 1.1.0), testthat (>= 3.0.0), knitr, rmarkdown, covr Luis Javier Madrigal-Roca <madrigalrocalj@yahoo.com> Comprehensive R Archive Network (CRAN) Luis Javier Madrigal-Roca [aut, cre], John Kelly [aut] MIT + file LICENSE (https://CRAN.R-project.org/package=ErrorTracer/LICENSE) 2026-05-04 application/tgz https://CRAN.R-project.org/package=ErrorTracer doi:10.32614/CRAN.package.ErrorTracer