Analysis of Bayesian adaptive enrichment clinical trial using Free-Knot Bayesian Model Averaging (FK-BMA) method of Maleyeff et al. (2024) for Gaussian data. Maleyeff, L., Golchi, S., Moodie, E. E. M., & Hudson, M. (2024) "An adaptive enrichment design using Bayesian model averaging for selection and threshold-identification of predictive variables" <doi:10.1093/biomtc/ujae141>.

This package implements a novel approach for measuring feature importance in k-means clustering. Importance of a feature is measured by the misclassification rate relative to the baseline cluster assignment due to a random permutation of feature values. An explanation of permutation feature importance in general can be found here: <https://christophm.github.io/interpretable-ml-book/feature-importance.html>.

Computes Fourier integrals of functions of one and two variables using the Fast Fourier transform. The Fourier transforms must be evaluated on a regular grid for fast evaluation.

This package provides a collection of commonly used univariate and multivariate time series forecasting models including automatically selected exponential smoothing (ETS) and autoregressive integrated moving average (ARIMA) models. These models work within the fable framework provided by the fabletools package, which provides the tools to evaluate, visualise, and combine models in a workflow consistent with the tidyverse.

This package provides fast moving-window ("focal") and buffer-based extraction for raster data using the terra package. Automatically selects between a C++ backend (via terra') and a Fast Fourier Transform (FFT) backend depending on problem size. The FFT backend supports sum and mean, while other statistics (e.g., median, min, max, standard deviation) are handled by the terra backend. Supports multiple kernel types (e.g., circle, rectangle, gaussian), with NA handling consistent with terra via na.rm and na.policy'. Operates on SpatRaster objects and returns results with the same geometry.

TrainFastImputation() uses training data to describe a multivariate normal distribution that the data approximates or can be transformed into approximating and stores this information as an object of class FastImputationPatterns'. FastImputation() function uses this FastImputationPatterns object to impute (make a good guess at) missing data in a single line or a whole data frame of data. This approximates the process used by Amelia <https://gking.harvard.edu/amelia> but is much faster when filling in values for a single line of data.

Maximum Likelihood Estimation of Stochastic Frontier Production and Cost Functions. Two specifications are available: the error components specification with time-varying efficiencies (Battese and Coelli, 1992, <doi:10.1007/BF00158774>) and a model specification in which the firm effects are directly influenced by a number of variables (Battese and Coelli, 1995, <doi:10.1007/BF01205442>).

Function factories are functions that make functions. They can be confusing to construct. Straightforward techniques can produce functions that are fragile or hard to understand. While more robust techniques exist to construct function factories, those techniques can be confusing. This package is designed to make it easier to construct function factories.

Extracts and parses structured metadata ('YAML or TOML') from the beginning of text documents. Front matter is a common pattern in Quarto documents, R Markdown documents, static site generators, documentation systems, content management tools and even Python and R scripts where metadata is placed at the top of a document, separated from the main content by delimiter fences.

This package provides a collection of R games and other funny stuff, such as the classic Mine sweeper and sliding puzzles.

Easy way to plot regular/weighted/conditional distributions by using formulas. The core of the package concerns distribution plots which are automatic: the many options are tailored to the data at hand to offer the nicest and most meaningful graphs possible -- with no/minimum user input. Further provide functions to plot conditional trends and box plots. See <https://lrberge.github.io/fplot/> for more information.

Base maps are transformed to focus on a specific location using an azimuthal logarithmic distance transformation.

This package provides an implementation of finite mixture regression models for censored data under four distributional families: Normal (FM-NCR), Student t (FM-TCR), skew-Normal (FM-SNCR), and skew-t (FM-STCR). The package enables flexible modeling of skewness and heavy tails often observed in real-world data, while explicitly accounting for censoring. Functions are included for parameter estimation via the Expectation-Maximization (EM) algorithm, computation of standard errors, and model comparison criteria such as the Akaike Information Criterion (AIC), the Bayesian Information Criterion (BIC), and the Efficient Determination Criterion (EDC). The underlying methodology is described in Park et al. (2024) <doi:10.1007/s00180-024-01459-4>.

This package provides a fast Rcpp'-based implementation of polynomially-computable voting theory methods for committee ranking and scoring. The package includes methods such as Approval Voting (AV), Satisfaction Approval Voting (SAV), sequential Proportional Approval Voting (PAV), and sequential Phragmen's Rule. Weighted variants of these methods are also provided, allowing for differential voter influence.

Estimation and display of various types of population attributable fraction and impact fractions. As well as the usual calculations of attributable fractions and impact fractions, functions are provided for attributable fraction nomograms and fan plots, continuous exposures, for pathway specific population attributable fractions, and for joint, average and sequential population attributable fractions.

Estimates the parameters of a GARCH-X model with exogenous covariates, performs hypothesis tests for the parameters returning the p-values, and uses False Discovery Rate p-value corrections to select the exogenous variables.

This package provides a ggplot2'-consistent approach to generating 2D displays of volumetric brain imaging data. Display data from multiple NIfTI images using standard ggplot2 conventions such scales, limits, and themes to control the appearance of displays. The resulting plots are returned as patchwork objects, inheriting from ggplot', allowing for any standard modifications of display aesthetics supported by ggplot2'.

This package provides tools for semantic segmentation of geospatial data using convolutional neural network-based deep learning. Utility functions allow for creating masks, image chips, data frames listing image chips in a directory, and DataSets for use within DataLoaders. Additional functions are provided to serve as checks during the data preparation and training process. A UNet architecture can be defined with 4 blocks in the encoder, a bottleneck block, and 4 blocks in the decoder. The UNet can accept a variable number of input channels, and the user can define the number of feature maps produced in each encoder and decoder block and the bottleneck. Users can also choose to (1) replace all rectified linear unit (ReLU) activation functions with leaky ReLU or swish, (2) implement attention gates along the skip connections, (3) implement squeeze and excitation modules within the encoder blocks, (4) add residual connections within all blocks, (5) replace the bottleneck with a modified atrous spatial pyramid pooling (ASPP) module, and/or (6) implement deep supervision using predictions generated at each stage in the decoder. A unified focal loss framework is implemented after Yeung et al. (2022) <doi:10.1016/j.compmedimag.2021.102026>. We have also implemented assessment metrics using the luz package including F1-score, recall, and precision. Trained models can be used to predict to spatial data without the need to generate chips from larger spatial extents. Functions are available for performing accuracy assessment. The package relies on torch for implementing deep learning, which does not require the installation of a Python environment. Raster geospatial data are handled with terra'. Models can be trained using a Compute Unified Device Architecture (CUDA)-enabled graphics processing unit (GPU); however, multi-GPU training is not supported by torch in R'.

Gaussian copula models for count time series. Includes simulation utilities, likelihood approximation, maximum-likelihood estimation, residual diagnostics, and predictive inference. Implements the Time Series Minimax Exponential Tilting (TMET) method, an adaptation of Minimax Exponential Tilting (Botev, 2017) <doi:10.1111/rssb.12162> and the Vecchia-based tilting framework of Cao and Katzfuss (2025) <doi:10.1080/01621459.2025.2546586>. Also provides a linear-cost implementation of the Gewekeâ Hajivassiliouâ Keane (GHK) simulator inspired by Masarotto and Varin (2012) <doi:10.1214/12-EJS721>, and the Continuous Extension (CE) approximation of Nguyen and De Oliveira (2025) <doi:10.1080/02664763.2025.2498502>. The package follows the S3 structure of gcmr', but all code in gctsc was developed independently.

Routines that allow the user to run goodness of fit tests based on empirical distribution functions for formal model evaluation in a general likelihood model. In addition, functions are provided to test if a sample follows Normal or Gamma distributions, validate the normality assumptions in a linear model, and examine the appropriateness of a Gamma distribution in generalized linear models with various link functions. Michael Arthur Stephens (1976) <http://www.jstor.org/stable/2958206>.

Package for Genetic Epidemiologic Methods Developed at MSKCC. It contains functions to calculate haplotype specific odds ratio and the power of two stage design for GWAS studies.

Interface for extra smooth functions including tensor products, neural networks and decision trees.

Fit joint models of survival and multivariate longitudinal data. The longitudinal data is specified by generalised linear mixed models. The joint models are fit via maximum likelihood using an approximate expectation maximisation algorithm. Bernhardt (2015) <doi:10.1016/j.csda.2014.11.011>.

This package provides a unified framework for sparse-group regularization and precision matrix estimation in Gaussian graphical models. It implements multiple sparse-group penalties, including sparse-group lasso, sparse-group adaptive lasso, sparse-group SCAD, and sparse-group MCP, and solves them efficiently using ADMM-based optimization. The package is designed for high-dimensional network inference where both sparsity and group structure are present.