Provides tools to visualize ordination results in 'R' by adding covariance-based ellipses, centroids, vectors, and confidence regions to plots created with 'ggplot2'. The package extends the 'vegan' framework and supports Principal Component Analysis (PCA), Redundancy Analysis (RDA), and Non-metric Multidimensional Scaling (NMDS). Ellipses can represent either group dispersion (standard deviation, SD) or centroid precision (standard error, SE), following Wang et al. (2015) <doi:10.1371/journal.pone.0118537>. Robust estimators of covariance are implemented, including the Minimum Covariance Determinant (MCD) method of Hubert et al. (2018) <doi:10.1002/wics.1421>. This approach reduces the influence of outliers. barrel is particularly useful for multivariate ecological datasets, promoting reproducible, publication-quality ordination graphics with minimal effort.
Please use the canonical form https://CRAN.R-project.org/package=barrel to link to this page.