Post

🚀 Big updates are here! A new round of #rstats #easystats releases is now live on CRAN, featuring major performance boosts and new features for parameters, bayestestR, performance, modelbased, and see. Update via CRAN or grab the latest dev versions with: `easystats::install_latest()`

📊 {parameters} 0.29.1 is out! - Faster model_parameters() for large mgcv::gam() models (use re_test = FALSE) - Better handling of (Intercept) in post-hoc standardizations - Cluster argument in bootstrap_model() for parallel SNOW handling - Support for lavaan.mi & BSDA packages

🔮 {bayestestR} 0.18.1 brings better MCMC diagnostics! - diagnostic_posterior() now reports tail-ESS for more reliable credible intervals (pass "ESS_bulk" for bulk-ESS) - Works with raw MCMC samples - Expanded {cmdstanr} & {rstan} support - New matrix methods for Bayes factors

📈 {performance} 0.17.0 makes model evaluation even smoother: - test_likelihoodratio() now includes a -2LL criterion column - check_predictions() for Bayesian models is standardized using {modelbased} under the hood - Expanded troubleshooting docs for check_model()

🧠 {modelbased} 0.15.0 expands your contrast analysis: - estimate_contrasts() can now calculate contrasts of average slopes (great for within/between context effects!) - Added support for nestedLogit models - Visual tweak: join_dots in plot() now defaults to FALSE

🎨 {see} 0.14.0 levels up your visualizations! - New type = "graph" for factor analysis & PCA plots to map node/edge loadings - Brand new _halo() geoms (geom_point_halo(), etc.) to add sleek contours to points - Cleaned up smoother curves in outlier plots for small datasets