Structured Covariances Estimators for Pairwise and Spatial Covariates

Implements estimators for structured covariance matrices in the presence of pairwise and spatial covariates. Metodiev, Perrot-Dockès, Ouadah, Fosdick, Robin, Latouche & Raftery (2026) .

Sparse-Group Lasso via Semismooth Newton Augmented Lagrangian

Implements the sparse-group lasso method of Zhang et al. (2020) . Unlike many widely available methods based on first-order descent, this method uses second-order information to solve the dual optimization problem via a semismooth Newton method.

Regression and Classification Tools

Tools for linear, nonlinear and nonparametric regression and classification. Novel graphical methods for assessment of parametric models using nonparametric methods. One vs. All and All vs. All multiclass classification, optional class probabilities adjustment. Nonparametric regression (k-NN) for general dimension, local-linear option. Nonlinear regression with Eickert-White method for dealing with heteroscedasticity. Utilities for converting time series to rectangular form. Utilities for conversion between factors and indicator variables. Some code related to "Statistical Regression and Classification: from Linear Models to Machine Learning", N. Matloff, 2017, CRC, ISBN 9781498710916.

The Exterior Calculus

Provides functionality for working with tensors, alternating forms, wedge products, Stokes's theorem, and related concepts from the exterior calculus. Uses 'disordR' discipline (Hankin, 2022, ). The canonical reference would be M. Spivak (1965, ISBN:0-8053-9021-9) "Calculus on Manifolds". To cite the package in publications please use Hankin (2022) .

Ecological Drift under the UNTB

Hubbell's Unified Neutral Theory of Biodiversity.

Multivariate Polynomials

Various utilities to manipulate multivariate polynomials. The package is almost completely superceded by the 'spray' and 'mvp' packages, which are much more efficient.

How to Add Two R Tables

Methods to "add" two R tables; also an alternative interpretation of named vectors as generalized R tables, so that c(a=1,b=2,c=3) + c(b=3,a=-1) will return c(b=5,c=3). Uses 'disordR' discipline (Hankin, 2022, ). Extraction and replacement methods are provided. The underlying mathematical structure is the Free Abelian group, hence the name. To cite in publications please use Hankin (2023) .

A Multivariate Emulator

A multivariate generalization of the emulator package.

A Suite of Routines for Working with Jordan Algebras

A Jordan algebra is an algebraic object originally designed to study observables in quantum mechanics. Jordan algebras are commutative but non-associative; they satisfy the Jordan identity. The package follows the ideas and notation of K. McCrimmon (2004, ISBN:0-387-95447-3) "A Taste of Jordan Algebras". To cite the package in publications, please use Hankin (2023) .

Antiassociative Algebra

Methods to deal with the free antiassociative algebra over the reals with an arbitrary number of indeterminates. Antiassociativity means that (xy)z = -x(yz). Antiassociative algebras are nilpotent with nilindex four (Remm, 2022, ) and this drives the design and philosophy of the package. Methods are defined to create and manipulate arbitrary elements of the antiassociative algebra, and to extract and replace coefficients. A vignette is provided.