It provides functions that calculate Mahalanobis distance, Euclidean distance, Manhattan distance, Chebyshev distance, Hamming distance, Canberra distance, Minkowski dissimilarity (distance defined for p >= 1), Cosine dissimilarity, Bhattacharyya dissimilarity, Jaccard distance, Hellinger distance, Bray-Curtis dissimilarity, Sorensen-Dice dissimilarity between each pair of species in a list of data frames. These statistics are fundamental in various fields, such as cluster analysis, classification, and other applications of machine learning and data mining, where assessing similarity or dissimilarity between data is crucial. The package is designed to be flexible and easily integrated into data analysis workflows, providing reliable tools for evaluating distances in multidimensional contexts.

An algorithm of optimal subset selection, related to Covariance matrices, observation matrices and Response vectors (COR) to select the optimal subsets in distributed estimation. The philosophy of the package is described in Guo G. (2024) <doi:10.1007/s11222-024-10471-z>.

This package provides tools for performing consensus clustering on multiple imputed datasets. The package supports a range of clustering algorithms across imputations, including hierarchical methods (e.g., Ward, single, complete, average) and partition-based approaches such as k-means, k-medoids (PAM), fuzzy clustering, model-based clustering ('mclust'), and methods for mixed or categorical data (k-modes and k-prototypes). A co-assignment matrix is constructed to quantify agreement between partitions, and consensus solutions are derived via hierarchical clustering applied to the resulting dissimilarity matrix. Additional functions are provided for validation and visualization of clustering results, facilitating robust analysis in the presence of missing data. Consensus clustering framework is based on Monti et al. (2003) <doi:10.1023/A:1023949509487>, rank aggregation methods follow Pihur et al. (2007) <doi:10.1093/bioinformatics/btm158>, and the PAC (Proportion of Ambiguous Clustering) metric is based on Senbabaoglu et al. (2014) <doi:10.1038/srep06207>.

Estimation and inference for linear models where some or all of the fixed-effects coefficients are subject to order restrictions. This package uses the robust residual bootstrap methodology for inference, and can handle some structure in the residual variance matrix.

This package provides a set of radiative transfer models to quantitatively describe the absorption, reflectance and transmission of solar energy in vegetation, and model remotely sensed spectral signatures of vegetation at distinct spatial scales (leaf,canopy and stand). The main principle behind ccrtm is that many radiative transfer models can form a coupled chain, basically models that feed into each other in a linked chain (from leaf, to canopy, to stand, to atmosphere). It allows the simulation of spectral datasets in the solar spectrum (400-2500nm) using leaf models as PROSPECT5, 5b, and D which can be coupled with canopy models as FLIM', SAIL and SAIL2'. Currently, only a simple atmospheric model ('skyl') is implemented. Jacquemoud et al 2008 provide the most comprehensive overview of these models <doi:10.1016/j.rse.2008.01.026>.

This package provides a shortcut procedure is proposed to implement closed testing for large-scale multiple testings, especially with the global test. This shortcut is asymptotically equivalent to closed testing and post hoc. Users could detect any possible sets of features or pathways with family-wise error rate controlled. The global test is powerful to detect associations between a group of features and an outcome of interest.

This package provides a cookie is a piece of data sent from a web server to a web client which helps in overcoming the statelessness constraint of the HTTP protocol. This package provides the tools to work with them in the form of a cookie parser middleware function, meant to be attached to a bigger R web application, and utilities to write, sign and unsign a cookie. For more details see the Mozilla Developer Network (MDN) web documentation in <https://developer.mozilla.org/en-US/docs/Web/HTTP/Guides/Cookies>.

Conditional moments test, as proposed by Newey (1985) <doi:10.2307/1911011 > and Tauchen (1985) <doi:10.1016/0304-4076(85)90149-6>, useful to detect specification violations for models estimated by maximum likelihood. Methods for probit and tobit models are provided.

Pool cells together before running differentially expression (DE) analysis. Tell CellDEEP how many cells you want to pool together (which shall be determined by the overall cell number of data), then run DE analysis. Cheng et al. (2026) <doi:10.64898/2026.03.09.710522>.

Can be useful for finding associations among different positions in a position-wise aligned sequence dataset. The approach adopted for finding associations among positions is based on the latent multivariate normal distribution.

Estimates phylogenetic trees from allele count data using the root distance method under the Coalescent Model. Given a matrix of allele counts across taxa and loci, the package estimates pairwise root distances under the Coalescent Model using maximum likelihood estimation. Then, it estimates a labeled phylogenetic tree from the estimated root distances. See Peng et al. (2021) <doi:10.1016/j.ympev.2021.107142>.

Model-based clustering of mixed data (i.e. data which consist of continuous, binary, ordinal or nominal variables) using a parsimonious mixture of latent Gaussian variable models.

Bindings to Google's C++ library Compact Language Detector 2 (see <https://github.com/cld2owners/cld2#readme> for more information). Probabilistically detects over 80 languages in plain text or HTML. For mixed-language input it returns the top three detected languages and their approximate proportion of the total classified text bytes (e.g. 80% English and 20% French out of 1000 bytes). There is also a cld3 package on CRAN which uses a neural network model instead.

Variance estimation on indicators of income concentration and poverty using complex sample survey designs. Wrapper around the survey package.

Computes a structural similarity metric (after the style of MS-SSIM for images) for binary and categorical 2D and 3D images. Can be based on accuracy (simple matching), Cohen's kappa, Rand index, adjusted Rand index, Jaccard index, Dice index, normalized mutual information, or adjusted mutual information. In addition, has fast computation of Cohen's kappa, the Rand indices, and the two mutual informations. Implements the methods of Thompson and Maitra (2020) <doi:10.48550/arXiv.2004.09073>.

This package implements the Changepoints for a Range of Penalties (CROPS) algorithm of Haynes et al. (2017) <doi:10.1080/10618600.2015.1116445> for finding all of the optimal segmentations for multiple penalty values over a continuous range.

Computes a confidence interval for a specified linear combination of the regression parameters in a linear regression model with iid normal errors with known variance when there is uncertain prior information that a distinct specified linear combination of the regression parameters takes a given value. This confidence interval, found by numerical nonlinear constrained optimization, has the required minimum coverage and utilizes this uncertain prior information through desirable expected length properties. This confidence interval has the following three practical applications. Firstly, if the error variance has been accurately estimated from previous data then it may be treated as being effectively known. Secondly, for sufficiently large (dimension of the response vector) minus (dimension of regression parameter vector), greater than or equal to 30 (say), if we replace the assumed known value of the error variance by its usual estimator in the formula for the confidence interval then the resulting interval has, to a very good approximation, the same coverage probability and expected length properties as when the error variance is known. Thirdly, some more complicated models can be approximated by the linear regression model with error variance known when certain unknown parameters are replaced by estimates. This confidence interval is described in Mainzer, R. and Kabaila, P. (2019) <doi:10.32614/RJ-2019-026>, and is a member of the family of confidence intervals proposed by Kabaila, P. and Giri, K. (2009) <doi:10.1016/j.jspi.2009.03.018>.

Post-hoc fairness auditing toolkit for clinical prediction models. Unlike in-processing approaches that modify model training, this package evaluates existing models by computing group-wise fairness metrics (demographic parity, equalized odds, predictive parity, calibration disparity), visualizing disparities across protected attributes, and performing threshold-based mitigation. Supports intersectional analysis across multiple attributes and generates audit reports useful for fairness-oriented auditing in clinical AI settings. Methods described in Obermeyer et al. (2019) <doi:10.1126/science.aax2342> and Hardt, Price, and Srebro (2016) <doi:10.48550/arXiv.1610.02413>.

Create, query, and modify causal graphs. caugi (Causal Graph Interface) is a causality-first, high performance graph package that provides a simple interface to build, structure, and examine causal relationships.

Biotechnology in spatial omics has advanced rapidly over the past few years, enhancing both throughput and resolution. However, existing annotation pipelines in spatial omics predominantly rely on clustering methods, lacking the flexibility to integrate extensive annotated information from single-cell RNA sequencing (scRNA-seq) due to discrepancies in spatial resolutions, species, or modalities. Here we introduce the CAESAR suite, an open-source software package that provides image-based spatial co-embedding of locations and genomic features. It uniquely transfers labels from scRNA-seq reference, enabling the annotation of spatial omics datasets across different technologies, resolutions, species, and modalities, based on the conserved relationship between signature genes and cells/locations at an appropriate level of granularity. Notably, CAESAR enriches location-level pathways, allowing for the detection of gradual biological pathway activation within spatially defined domain types. More details on the methods related to our paper currently under submission. A full reference to the paper will be provided in future versions once the paper is published.

This package provides functions for evaluating and visualizing predictive model performance (specifically: binary classifiers) in the field of customer scoring. These metrics include lift, lift index, gain percentage, top-decile lift, F1-score, expected misclassification cost and absolute misclassification cost. See Berry & Linoff (2004, ISBN:0-471-47064-3), Witten and Frank (2005, 0-12-088407-0) and Blattberg, Kim & Neslin (2008, ISBN:978â 0â 387â 72578â 9) for details. Visualization functions are included for lift charts and gain percentage charts. All metrics that require class predictions offer the possibility to dynamically determine cutoff values for transforming real-valued probability predictions into class predictions.

Compute expected shortfall (ES) and Value at Risk (VaR) from a quantile function, distribution function, random number generator, probability density function, or data. ES is also known as Conditional Value at Risk (CVaR). Virtually any continuous distribution can be specified. The functions are vectorized over the arguments. The computations are done directly from the definitions, see e.g. Acerbi and Tasche (2002) <doi:10.1111/1468-0300.00091>. Some support for GARCH models is provided, as well.

Modeling associations between covariates and power spectra of replicated time series using a cepstral-based semiparametric framework. Implements a fast two-stage estimation procedure via Whittle likelihood and multivariate regression.The methodology is based on Li and Dong (2025) <doi:10.1080/10618600.2025.2473936>.

This package performs the calibration procedure proposed by Sung et al. (2018+) <arXiv:1806.01453>. This calibration method is particularly useful when the outputs of both computer and physical experiments are binary and the estimation for the calibration parameters is of interest.