Model fitting and evaluation tools for double generalized linear models (DGLMs). This class of models uses one generalized linear model (GLM) to fit the specified response and a second GLM to fit the deviance of the first model.

Solving large scale distance weighted discrimination. The main algorithm is a symmetric Gauss-Seidel based alternating direction method of multipliers (ADMM) method. See Lam, X.Y., Marron, J.S., Sun, D.F., and Toh, K.C. (2018) <doi:10.48550/arXiv.1604.05473> for more details.

Density surface modelling of line transect data. A Generalized Additive Model-based approach is used to calculate spatially-explicit estimates of animal abundance from distance sampling (also presence/absence and strip transect) data. Several utility functions are provided for model checking, plotting and variance estimation.

Discriminant Adaptive Nearest Neighbor Classification is a variation of k nearest neighbors where the shape of the neighborhood is data driven. This package implements dann and sub_dann from Hastie (1996) <https://web.stanford.edu/~hastie/Papers/dann_IEEE.pdf>.

This package provides tools for detecting, decomposing, and stress-testing temporal drift in repeated binary decision systems. Complements the decisionpaths package by shifting focus from path construction to system-level change over time. Implements five core analytic modules: (1) prevalence drift â did the overall decision rate change over time?; (2) transition drift â did the probability of switching or persisting change?; (3) entropy and stability trends â did path complexity evolve?; (4) group-differential drift â did the system drift differently across subgroups?; (5) change-point and regime-shift detection â did the system change abruptly after a policy or model update? Additionally provides a robustness module for testing stability of drift conclusions across analytic choices, and a sensitivity module for probing vulnerability to data problems including missingness, miscoding, and threshold shifts. Defines four original drift indices: the Decision Drift Index (DDI), Transition Drift Index (TDI), Group Differential Drift (GDD), and Cumulative Drift Burden (CDB). Applications include algorithmic audit, AI governance, education, health, and organisational research.

The natural increase in the complexity of current research experiments and data demands better tools to enhance productivity in Data Analytics. The package is a framework designed to address the modern challenges in data analytics workflows. The package is inspired by Experiment Line concepts. It aims to provide seamless support for users in developing their data mining workflows by offering a uniform data model and method API. It enables the integration of various data mining activities, including data preprocessing, classification, regression, clustering, and time series prediction. It also offers options for hyper-parameter tuning and supports integration with existing libraries and languages. Overall, the package provides researchers with a comprehensive set of functionalities for data science, promoting ease of use, extensibility, and integration with various tools and libraries. Information on Experiment Line is based on Ogasawara et al. (2009) <doi:10.1007/978-3-642-02279-1_20>.

This package provides a collection of functions for directional data (including massive data, with millions of observations) analysis. Hypothesis testing, discriminant and regression analysis, MLE of distributions and more are included. The standard textbook for such data is the "Directional Statistics" by Mardia, K. V. and Jupp, P. E. (2000). Other references include: a) Paine J.P., Preston S.P., Tsagris M. and Wood A.T.A. (2018). "An elliptically symmetric angular Gaussian distribution". Statistics and Computing 28(3): 689-697. <doi:10.1007/s11222-017-9756-4>. b) Tsagris M. and Alenazi A. (2019). "Comparison of discriminant analysis methods on the sphere". Communications in Statistics: Case Studies, Data Analysis and Applications 5(4):467--491. <doi:10.1080/23737484.2019.1684854>. c) Paine J.P., Preston S.P., Tsagris M. and Wood A.T.A. (2020). "Spherical regression models with general covariates and anisotropic errors". Statistics and Computing 30(1): 153--165. <doi:10.1007/s11222-019-09872-2>. d) Tsagris M. and Alenazi A. (2024). "An investigation of hypothesis testing procedures for circular and spherical mean vectors". Communications in Statistics-Simulation and Computation, 53(3): 1387--1408. <doi:10.1080/03610918.2022.2045499>. e) Yu Z. and Huang X. (2024). A new parameterization for elliptically symmetric angular Gaussian distributions of arbitrary dimension. Electronic Journal of Statistics, 18(1): 301--334. <doi:10.1214/23-EJS2210>. f) Tsagris M. and Alzeley O. (2025). "Circular and spherical projected Cauchy distributions: A Novel Framework for Circular and Directional Data Modeling". Australian & New Zealand Journal of Statistics, 67(1): 77--103. <doi:10.1111/anzs.12434>. g) Tsagris M., Papastamoulis P. and Kato S. (2025). "Directional data analysis: spherical Cauchy or Poisson kernel-based distribution". Statistics and Computing, 35:51. <doi:10.1007/s11222-025-10583-0>. h) Alzeley O. and Tsagris (2026). "On the generalized circular projected Cauchy distribution". Mathematics, 14(11): 1934. <doi:10.3390/math14111934>.

Allows users to quickly and easily describe data using common descriptive statistics.

This package provides a two-stage procedure for the denoising and clustering of stack of noisy images acquired over time. Clustering only assumes that the data contain an unknown but small number of dynamic features. The method first denoises the signals using local spatial and full temporal information. The clustering step uses the previous output to aggregate voxels based on the knowledge of their spatial neighborhood. Both steps use a single keytool based on the statistical comparison of the difference of two signals with the null signal. No assumption is therefore required on the shape of the signals. The data are assumed to be normally distributed (or at least follow a symmetric distribution) with a known constant variance. Working pixelwise, the method can be time-consuming depending on the size of the data-array but harnesses the power of multicore cpus.

This package provides a toolbox to create and manage metadata files and configuration profiles: files used to configure the parameters and initial settings for some computer programs.

This package implements distributional cost-effectiveness analysis (DCEA) as described in Cookson et al. (2020, ISBN:9780198838197) and the methods endorsed by NICE (2025) for health technology evaluation. Provides functions for both aggregate and full-form DCEA, inequality measurement (Atkinson index, Gini coefficient, slope index of inequality, relative index of inequality), social welfare function evaluation, equity-efficiency impact plane visualisation, and sensitivity analysis over inequality aversion parameters. Includes baseline health distributions for England (by IMD quintile), Canada (income quintile), and global WHO regions. Suitable for academic research, health technology assessment submissions, and public health policy analysis.

Models the relationship between dose levels and responses in a pharmacological experiment using the 4 Parameter Logistic model. Traditional packages on dose-response modelling such as drc and nplr often draw errors due to convergence failure especially when data have outliers or non-logistic shapes. This package provides robust estimation methods that are less affected by outliers and other initialization methods that work well for data lacking logistic shapes. We provide the bounds on the parameters of the 4PL model that prevent parameter estimates from diverging or converging to zero and base their justification in a statistical principle. These methods are used as remedies to convergence failure problems. Gadagkar, S. R. and Call, G. B. (2015) <doi:10.1016/j.vascn.2014.08.006> Ritz, C. and Baty, F. and Streibig, J. C. and Gerhard, D. (2015) <doi:10.1371/journal.pone.0146021>.

Supports import/export for a number of datetime string standards and R datetime classes often including lossless re-export of any original reduced precision including ISO 8601 <https://en.wikipedia.org/wiki/ISO_8601> and pdfmark <https://opensource.adobe.com/dc-acrobat-sdk-docs/library/pdfmark/> datetime strings. Supports local/global datetimes with optional UTC offsets and/or (possibly heterogeneous) time zones with up to nanosecond precision.

Simplifies and automates the process of exploring and merging data from relational databases. This package allows users to discover table relationships, create a map of all possible joins, and generate executable plans to merge data based on a structured metadata framework.

In applications it is usual that some additional information is available. This package dawai (an acronym for Discriminant Analysis With Additional Information) performs linear and quadratic discriminant analysis with additional information expressed as inequality restrictions among the populations means. It also computes several estimations of the true error rate.

This package provides a big-data-friendly and memory-efficient difference-in-differences estimator for staggered (and non-staggered) treatment contexts.

Density ratio estimation. The estimated density ratio function can be used in many applications such as anomaly detection, change-point detection, covariate shift adaptation. The implemented methods are uLSIF (Hido et al. (2011) <doi:10.1007/s10115-010-0283-2>), RuLSIF (Yamada et al. (2011) <doi:10.1162/NECO_a_00442>), and KLIEP (Sugiyama et al. (2007) <doi:10.1007/s10463-008-0197-x>).

Efficient estimation of Dynamic Factor Models using the Expectation Maximization (EM) algorithm or Two-Step (2S) estimation, supporting datasets with missing data and mixed-frequency nowcasting applications. Factors follow a stationary VAR process of order p. Estimation options include: running the Kalman Filter and Smoother once with PCA initial values (2S) as in Doz, Giannone and Reichlin (2011) <doi:10.1016/j.jeconom.2011.02.012>; iterated Kalman Filtering and Smoothing until EM convergence as in Doz, Giannone and Reichlin (2012) <doi:10.1162/REST_a_00225>; or the adapted EM algorithm of Banbura and Modugno (2014) <doi:10.1002/jae.2306>, allowing arbitrary missing-data patterns and monthly-quarterly mixed-frequency datasets. The implementation uses the Armadillo C++ library and the collapse package for fast estimation. A comprehensive set of methods supports interpretation and visualization, forecasting, and decomposition of the news content of macroeconomic data releases following Banbura and Modugno (2014). Information criteria to choose the number of factors are also provided, following Bai and Ng (2002) <doi:10.1111/1468-0262.00273>.

Classical Test and Item analysis, Item Response analysis and data management for educational and psychological tests.

An R DataBase Interface ('DBI') compatible interface to various database platforms ('PostgreSQL', Oracle', Microsoft SQL Server', Amazon Redshift', Microsoft Parallel Database Warehouse', IBM Netezza', Apache Impala', Google BigQuery', Snowflake', Spark', SQLite', and InterSystems IRIS'). Also includes support for fetching data as Andromeda objects. Uses either Java Database Connectivity ('JDBC') or other DBI drivers to connect to databases.

Doubly censored data, as described in Chang and Yang (1987) <doi: 10.1214/aos/1176350608>), are commonly seen in many fields. We use EM algorithm to compute the non-parametric MLE (NPMLE) of the cummulative probability function/survival function and the two censoring distributions. One can also specify a constraint F(T)=C, it will return the constrained NPMLE and the -2 log empirical likelihood ratio for this constraint. This can be used to test the hypothesis about the constraint and, by inverting the test, find confidence intervals for probability or quantile via empirical likelihood ratio theorem. Influence functions of hat F may also be calculated, but currently, the it may be slow.

This package implements fast Monte Carlo simulations for goodness-of-fit (GOF) tests for discrete distributions. This includes tests based on the Chi-squared statistic, the log-likelihood-ratio (G^2) statistic, the Freeman-Tukey (Hellinger-distance) statistic, the Kolmogorov-Smirnov statistic, the Cramer-von Mises statistic as described in Choulakian, Lockhart and Stephens (1994) <doi:10.2307/3315828>, and the root-mean-square statistic, see Perkins, Tygert, and Ward (2011) <doi:10.1016/j.amc.2011.03.124>.

This package implements the de-biased estimator for low-rank matrix completion and provides confidence intervals for entries of interest. See: by Chen et al. (2019) <doi:10.1073/pnas.1910053116>, Mai (2021) <arXiv:2103.11749>.

This package provides a metric called Density-Based Clustering Validation index (DBCV) index to evaluate clustering results, following the <https://github.com/pajaskowiak/clusterConfusion/blob/main/R/dbcv.R> R implementation by Pablo Andretta Jaskowiak. Original DBCV index article: Moulavi, D., Jaskowiak, P. A., Campello, R. J., Zimek, A., and Sander, J. (April 2014), "Density-based clustering validation", Proceedings of SDM 2014 -- the 2014 SIAM International Conference on Data Mining (pp. 839-847), <doi:10.1137/1.9781611973440.96>. A more recent article on the DBCV index: Chicco, D., Sabino, G.; Oneto, L.; Jurman, G. (August 2025), "The DBCV index is more informative than DCSI, CDbw, and VIASCKDE indices for unsupervised clustering internal assessment of concave-shaped and density-based clusters", PeerJ Computer Science 11:e3095 (pp. 1-), <doi:10.7717/peerj-cs.3095>.