This package provides a tool for computing probabilities and other quantities that are relevant in selecting performance criteria for discrete trial training. The main function, miebl(), computes Bayesian and frequentist probabilities and bounds for each of n possible performance criterion choices when attempting to determine a student's true mastery level by counting their number of successful attempts at displaying learning among n trials. The reporting function miebl_re() takes output from miebl() and prepares it into a brief report for a specific criterion. miebl_cp() combines 2 to 5 distributions of true mastery level given performance criterion in one plot for comparison. Ramos (2025) <doi:10.1007/s40617-025-01058-9>.

Slacks-based data envelopment analysis for panel data in which the reference set is an explicit argument. A user-supplied weight matrix, or a matrix learned from the data by penalised non-negative reconstruction, selects the units that may enter each decision-making unit's frontier. The package reports the unrestricted and the restricted score, the ratio of the two and an exact decomposition of the shortfall into the part the restricted technology can remove and the part it cannot. Moran's I and local indicators of spatial association are provided as diagnostics. All linear programs are solved by a two-phase simplex with Bland's rule implemented in R, so the package needs no compiler.

Consolidates and calculates different sets of time-series features from multiple R and Python packages including Rcatch22 Henderson, T. (2021) <doi:10.5281/zenodo.5546815>, feasts O'Hara-Wild, M., Hyndman, R., and Wang, E. (2021) <https://CRAN.R-project.org/package=feasts>, tsfeatures Hyndman, R., Kang, Y., Montero-Manso, P., Talagala, T., Wang, E., Yang, Y., and O'Hara-Wild, M. (2020) <https://CRAN.R-project.org/package=tsfeatures>, tsfresh Christ, M., Braun, N., Neuffer, J., and Kempa-Liehr A.W. (2018) <doi:10.1016/j.neucom.2018.03.067>, TSFEL Barandas, M., et al. (2020) <doi:10.1016/j.softx.2020.100456>, and Kats Facebook Infrastructure Data Science (2021) <https://facebookresearch.github.io/Kats/>.

The classical two-sample t-test works well for the normally distributed data or data with large sample size. The tcfu() and tt() tests implemented in this package provide better type-I-error control with more accurate power when testing the equality of two-sample means for skewed populations having unequal variances. These tests are especially useful when the sample sizes are moderate. The tcfu() uses the Cornish-Fisher expansion to achieve a better approximation to the true percentiles. The tt() provides transformations of the Welch's t-statistic so that the sampling distribution become more symmetric. For more technical details, please refer to Zhang (2019) <http://hdl.handle.net/2097/40235>.

Computes Chatterjee's non-parametric correlation coefficient for time series data. It extends the original metric to time series analysis by providing the univariate Xi-Autocorrelation Function (Xi-ACF), directional Xi-Cross-Correlation Function (Xi-CCF), and multivariate network evaluation matrices. The package allows users to test for non-linear dependence using Iterative Amplitude Adjusted Fourier Transform (IAAFT) and Multivariate IAAFT (MIAAFT) surrogate data with strict Family-Wise Error Rate ('FWER') control via Max-statistic approaches. Methodologies are based on Chatterjee (2021) <doi:10.1080/01621459.2020.1758115>, surrogate data testing methods by Schreiber and Schmitz (1996) <doi:10.1103/PhysRevLett.77.635>, and local structural identification by Watanabe (2026) <doi:10.2139/ssrn.6829431>.

The skewr package is a tool for visualizing the output of the Illumina Human Methylation 450k BeadChip to aid in quality control. It creates a panel of nine plots. Six of the plots represent the density of either the methylated intensity or the unmethylated intensity given by one of three subsets of the 485,577 total probes. These subsets include Type I-red, Type I-green, and Type II.The remaining three distributions give the density of the Beta-values for these same three subsets. Each of the nine plots optionally displays the distributions of the "rs" SNP probes and the probes associated with imprinted genes as series of tick marks located above the x-axis.

The developed function is a comprehensive tool for the analysis of India Meteorological Department (IMD) NetCDF rainfall data. Specifically designed to process high-resolution daily gridded rainfall datasets. It provides four key functions to process IMD NetCDF rainfall data and create rasters for various temporal scales, including annual, seasonal, monthly, and weekly rainfall. For method details see, Malik, A. (2019).<DOI:10.1007/s12517-019-4454-5>. It supports different aggregation methods, such as sum, min, max, mean, and standard deviation. These functions are designed for spatio-temporal analysis of rainfall patterns, trend analysis,geostatistical modeling of rainfall variability, identifying rainfall anomalies and extreme events and can be an input for hydrological and agricultural models.

This package implements the Capability-Ecological Developmental Model (CEDM) for longitudinal and multilevel data. The package supports estimation and interpretation of models examining how socioeconomic status (SES), health indicators, and contextual factors jointly relate to academic outcomes. Functionality includes: (1) classification of ecological capability regimes (amplifying, neutral, compensatory); (2) estimation of moderated multilevel models with higher-order interaction terms; (3) causal mediation analysis using doubly robust estimation; (4) random-effects within-between (REWB) decomposition; (5) nonlinear moderation using restricted cubic splines; (6) clustering of longitudinal health trajectories; and (7) sensitivity analysis using the impact threshold for a confounding variable (ITCV) and robustness-to-replacement (RIR) measures. The package is designed for use with general longitudinal multilevel datasets.

This package provides a d-statistic tests the null hypothesis of no treatment effect in a matched, nonrandomized study of the effects caused by treatments. A d-statistic focuses on subsets of matched pairs that demonstrate insensitivity to unmeasured bias in such an observational study, correcting for double-use of the data by conditional inference. This conditional inference can, in favorable circumstances, substantially increase the power of a sensitivity analysis (Rosenbaum (2010) <doi:10.1007/978-1-4419-1213-8_14>). There are two examples, one concerning unemployment from Lalive et al. (2006) <doi:10.1111/j.1467-937X.2006.00406.x>, the other concerning smoking and periodontal disease from Rosenbaum (2017) <doi:10.1214/17-STS621>.

The functions compute the double-entry intraclass correlation, which is an index of profile similarity (Furr, 2010; McCrae, 2008). The double-entry intraclass correlation is a more precise index of the agreement of two empirically observed profiles than the often-used intraclass correlation (McCrae, 2008). Profiles comprising correlations are automatically transformed according to the Fisher z-transformation before the double-entry intraclass correlation is calculated. If the profiles comprise scores such as sum scores from various personality scales, it is recommended to standardize each individual score prior to computation of the double-entry intraclass correlation (McCrae, 2008). See Furr (2010) <doi:10.1080/00223890903379134> or McCrae (2008) <doi:10.1080/00223890701845104> for details.

Map image classification efficacy (MICE) adjusts the accuracy rate relative to a random classification baseline (Shao et al. (2021)<doi:10.1109/ACCESS.2021.3116526> and Tang et al. (2024)<doi:10.1109/TGRS.2024.3446950>). Only the proportions from the reference labels are considered, as opposed to the proportions from the reference and predictions, as is the case for the Kappa statistic. This package offers means to calculate MICE and adjusted versions of class-level user's accuracy (i.e., precision) and producer's accuracy (i.e., recall) and F1-scores. Class-level metrics are aggregated using macro-averaging. Functions are also made available to estimate confidence intervals using bootstrapping and statistically compare two classification results.

This package implements various methods for eliciting a probability distribution for a single parameter from an expert or a group of experts. The expert provides a small number of probability judgements, corresponding to points on his or her cumulative distribution function. A range of parametric distributions can then be fitted and displayed, with feedback provided in the form of fitted probabilities and percentiles. For multiple experts, a weighted linear pool can be calculated. Also includes functions for eliciting beliefs about population distributions; eliciting multivariate distributions using a Gaussian copula; eliciting a Dirichlet distribution; eliciting distributions for variance parameters in a random effects meta-analysis model; survival extrapolation. R Shiny apps for most of the methods are included.

This package provides a fast and efficient implementation of Sobol sequences for quasi-Monte Carlo methods. The Sobol sequence is a low-discrepancy sequence with the property that for all values of N, its subsequence x1, ..., xN has a low discrepancy. It can be used to generate quasi-random numbers for use in Monte Carlo integration and other simulation methods. This implementation is based on the algorithms described by Bratley and Fox (1988) <doi:10.1145/42288.214372> and uses direction numbers from Joe and Kuo (2008) <doi:10.1145/1358628.1358630>. The package includes both batch and incremental interfaces with support for arbitrary starting indices and reproducible sequences. It uses Rcpp for efficient C++ integration.

Fit linear, logistic and Cox models regularized with L0, lasso (L1), elastic-net (L1 and L2), or net (L1 and Laplacian) penalty, and their adaptive forms, such as adaptive lasso / elastic-net and net adjusting for signs of linked coefficients. It solves the L0 penalty problem by simultaneously selecting regularization parameters and performing hard-thresholding or selecting the number of non-zeros. This augmented and penalized minimization method provides an approximation solution to the L0 penalty problem, but runs as fast as L1 regularization. The package uses a one-step coordinate descent algorithm and runs extremely fast by taking into account the sparsity structure of coefficients. It can handle very high dimensional data and has superior selection performance.

This package performs binary classification via Group Method of Data Handling (GMDH) - type neural network algorithms. There exist two main algorithms available in GMDH() and dceGMDH() functions. GMDH() performs classification via GMDH algorithm for a binary response and returns important variables. dceGMDH() performs classification via diverse classifiers ensemble based on GMDH (dce-GMDH) algorithm. Also, the package produces a well-formatted table of descriptives for a binary response. Moreover, it produces confusion matrix, its related statistics and scatter plot (2D and 3D) with classification labels of binary classes to assess the prediction performance. All GMDH2 functions are designed for a binary response (Dag et al., 2019, <https://download.atlantis-press.com/article/125911202.pdf>).

Data and utilities for estimating pediatric blood pressure percentiles by sex, age, and optionally height (stature) as described in Martin et al. (2022) <doi:10.1001/jamanetworkopen.2022.36918>. Blood pressure percentiles for children under one year of age come from Gemelli et al. (1990) <doi:10.1007/BF02171556>. Estimates of blood pressure percentiles for children at least one year of age are informed by data from the National Heart, Lung, and Blood Institute (NHLBI) and the Centers for Disease Control and Prevention (CDC) <doi:10.1542/peds.2009-2107C> or from Lo et al. (2013) <doi:10.1542/peds.2012-1292>. The source-selection flowchart comes from Martin et al. (2022) <doi:10.1542/hpeds.2021-005998>.

This package is a implementation of biclustering ensemble method MoSBi (Molecular signature Identification from Biclustering). MoSBi provides standardized interfaces for biclustering results and can combine their results with a multi-algorithm ensemble approach to compute robust ensemble biclusters on molecular omics data. This is done by computing similarity networks of biclusters and filtering for overlaps using a custom error model. After that, the louvain modularity it used to extract bicluster communities from the similarity network, which can then be converted to ensemble biclusters. Additionally, MoSBi includes several network visualization methods to give an intuitive and scalable overview of the results. MoSBi comes with several biclustering algorithms, but can be easily extended to new biclustering algorithms.

This package provides a compact C++ backend for Approximate Bayesian Computation (ABC) with a thin R frontend. The current implementation is primarily a C++ reimplementation of offline ABC workflows provided by the R abc package <doi:10.32614/CRAN.package.abc>, with the public R interface intentionally kept small and centered on abc() and summary() methods. The computational work is performed by shared C++ code. In addition to reproducing common abc workflows, the package adds optional dimensionality reduction of summary statistics through Principal Component Analysis (PCA) and Partial Least Squares (PLS), following related ideas described by Bazin et al. (2010) <doi:10.1534/genetics.109.112391> and Wegmann et al. (2009) <doi:10.1534/genetics.109.102509>.

This package provides a set of tools to perform Ecological Niche Modeling with presence-absence data. It includes algorithms for data partitioning, model fitting, calibration, evaluation, selection, and prediction. Other functions help to explore signals of ecological niche using univariate and multivariate analyses, and model features such as variable response curves and variable importance. Unique characteristics of this package are the ability to exclude models with concave quadratic responses, and the option to clamp model predictions to specific variables. These tools are implemented following principles proposed in Cobos et al., (2022) <doi:10.17161/bi.v17i.15985>, Cobos et al., (2019) <doi:10.7717/peerj.6281>, and Peterson et al., (2008) <doi:10.1016/j.ecolmodel.2007.11.008>.

The accurate annotation of genes and Quantitative Trait Loci (QTLs) located within candidate markers and/or regions (haplotypes, windows, CNVs, etc) is a crucial step the most common genomic analyses performed in livestock, such as Genome-Wide Association Studies or transcriptomics. The Genomic Annotation in Livestock for positional candidate LOci (GALLO) is an R package designed to provide an intuitive and straightforward environment to annotate positional candidate genes and QTLs from high-throughput genetic studies in livestock. Moreover, GALLO allows the graphical visualization of gene and QTL annotation results, data comparison among different grouping factors (e.g., methods, breeds, tissues, statistical models, studies, etc.), and QTL enrichment in different livestock species including cattle, pigs, sheep, and chicken, among others.

This package provides R bindings to the GGML tensor library for machine learning, optimized for Vulkan GPU acceleration with a transparent CPU fallback. The package features a Keras'-like sequential API and a PyTorch'-style autograd engine for building, training, and deploying neural networks. Key capabilities include high-performance 5D tensor operations, f16 precision, and efficient quantization. It supports native ONNX model import (50+ operators) and GGUF weight loading from the llama.cpp and Hugging Face ecosystems. Designed for zero-overhead inference via dedicated weight buffering, it integrates seamlessly as a parsnip engine for tidymodels and provides first-class learners for the mlr3 framework. See <https://github.com/ggml-org/ggml> for more information about the underlying library.

Conducting Line transect-based one-dimensional nearest neighbor distance and conducting hypothesis testing related to local distributional aggregation pattern of species. The reason that such a package is needed is because traditional two-dimensional nearest neighbor distance is not applicable when biodiversity data are sampled via optimal ecological survey methods, like line transects. In comparison to the entire studied region, line transect-collected local biodiversity data are spatially constrained and sampling-limited. To this end, two-dimensional nearest neighbor distance would tend to over-estimate distributional aggregation pattern of species when using this limited biodiversity information. Accordingly, one-dimensional nearest neighbor distance is needed and the associated statistical testing should be established for analyzing line transect-derived biodiversity data.

Solves the Multi-Criteria Minimum Spanning Tree (mc-MST) problem on complete weighted graphs by combining the Non-dominated Sorting Genetic Algorithm II (NSGA-II) with optional Pareto local search operators. Chromosomes are represented as Prufer sequences so that every random individual decodes to a valid spanning tree (Cayley's theorem), avoiding repair operators. Four solver variants are provided: pure NSGA-II ("base"), Path Relinking ("PR"), Pareto Local Search ("PLS"), and Tabu Search ("TS"). The package supports 2 and 3 objective formulations and provides convenience functions to plot Pareto fronts and best-compromise spanning trees. This package is the reference implementation of the method described in Parraga-Alava, Inostroza-Ponta and Dorn (2017) <doi:10.1109/CEC.2017.7969432>.

Performs unconditional exact tests and power calculations for 2x2 contingency tables. For comparing two independent proportions, performs Barnard's test (1945) using the original CSM test (Barnard (1947)), using Fisher's p-value referred to as Boschloo's test (1970), or using a Z-statistic (Suissa and Shuster (1985)). For comparing two binary proportions, performs unconditional exact test using McNemar's Z-statistic (Berger and Sidik (2003)), using McNemar's Z-statistic with continuity correction, or using CSM test. Calculates confidence intervals for the difference in proportion.