Various methods for multivariate outlier detection: arw, a Mahalanobis-type method with an adaptive outlier cutoff value; locout, a method incorporating local neighborhood; pcout, a method for high-dimensional data; mvoutlier.CoDa, a method for compositional data. References are provided in the corresponding help files.

This package provides fundamental functions for descriptive statistics, including MODE(), estimate_mode(), center_stats(), position_stats(), pct(), spread_stats(), kurt(), skew(), and shape_stats(), which assist in summarizing the center, spread, and shape of numeric data. For more details, see McCurdy (2025), "Introduction to Data Science with R" <https://jonmccurdy.github.io/Introduction-to-Data-Science/>.

Computes regression deletion diagnostics for multivariate linear models and provides some associated diagnostic plots. The diagnostic measures include hat-values (leverages), generalized Cook's distance, and generalized squared studentized residuals. Several types of plots to detect influential observations are provided.

Exploratory model analysis with <http://ggobi.org>. Fit and graphical explore ensembles of linear models.

Generate central composite designs (CCD)with full as well as fractional factorial points (half replicate) and Box Behnken designs (BBD) with minimally changed run sequence.

Package for estimating, analyzing, and forecasting multi-country macro-finance affine term structure models (ATSMs). All setups build on the single-country unspanned macroeconomic risk framework from Joslin, Priebsch, and Singleton (2014, JF) <doi:10.1111/jofi.12131>. Multicountry extensions by Jotikasthira, Le, and Lundblad (2015, JFE) <doi:10.1016/j.jfineco.2014.09.004>, Candelon and Moura (2023, EM) <doi:10.1016/j.econmod.2023.106453>, and Candelon and Moura (2024, JFEC) <doi:10.1093/jjfinec/nbae008> are also available. The package also provides tools for bias correction as in Bauer Rudebusch and Wu (2012, JBES) <doi:10.1080/07350015.2012.693855>, bootstrap analysis, and several graphical/numerical outputs.

In the MeLiDos field study, personal light exposure data were collected in 9 sites, 7 countries, and 196 participants following the Guidolin et al. (2024) <doi:10.1186/s12889-024-20206-4> protocol. Data originate from wearable devices collecting personal light exposure at the eye level, chest, and the wrist. Questionnaires were collected via REDCap and contain demographic information as well as chronotype, current conditions, sleep diaries, wear logs, and many more. This package makes loading the data from the respective repositories (<https://github.com/MeLiDosProject>) into R a breeze. It further contains some quality of life functions for label handling and data from REDCap'.

Maximum likelihood estimation for generalized linear mixed models via Monte Carlo EM. For a description of the algorithm see Brian S. Caffo, Wolfgang Jank and Galin L. Jones (2005) <DOI:10.1111/j.1467-9868.2005.00499.x>.

Estimation and bootstrap utilities for single layer and multilayer Mixed Graphical Models, including functions for centrality, bridge metrics, membership stability, and plotting (De Martino et al. (2026) <doi:10.48550/arXiv.2602.05716>).

Fits a geographically weighted regression model with different scales for each covariate. Uses the negative binomial distribution as default, but also accepts the normal, Poisson, or logistic distributions. Can fit the global versions of each regression and also the geographically weighted alternatives with only one scale, since they are all particular cases of the multiscale approach. Hanchen Yu (2024). "Exploring Multiscale Geographically Weighted Negative Binomial Regression", Annals of the American Association of Geographers <doi:10.1080/24694452.2023.2289986>. Fotheringham AS, Yang W, Kang W (2017). "Multiscale Geographically Weighted Regression (MGWR)", Annals of the American Association of Geographers <doi:10.1080/24694452.2017.1352480>. Da Silva AR, Rodrigues TCV (2014). "Geographically Weighted Negative Binomial Regression - incorporating overdispersion", Statistics and Computing <doi:10.1007/s11222-013-9401-9>.

This package provides an extensible framework for conducting simulations to compare data generating processes, item selection algorithms, parameter update algorithms, and stopping rules in computer adaptive testing (CAT) applications. Bundled algorithms include the Elo-based update rules of Klinkenberg, Straatemeier and van der Maas (2011) <doi:10.1016/j.compedu.2011.02.003> and Vermeiren, Kruis, Bolsinova, van der Maas and Hofman (2025) <doi:10.1016/j.caeai.2025.100376>.

Function and support for medication and dosing information extraction from free-text clinical notes. Medication entities for the basic medExtractR implementation that can be extracted include drug name, strength, dose amount, dose, frequency, intake time, dose change, and time of last dose. The basic medExtractR is outlined in Weeks, Beck, McNeer, Williams, Bejan, Denny, Choi (2020) <doi: 10.1093/jamia/ocz207>. The extended medExtractR_tapering implementation is intended to extract dosing information for more tapering schedules, which are far more complex. The tapering extension allows for the extraction of additional entities including dispense amount, refills, dose schedule, time keyword, transition, and preposition.

With foundations on the work by Goutali and Chebana (2024) <doi:10.1016/j.envsoft.2024.106090>, this package contains various univariate and multivariate trend tests. The main functions regard the Multivariate Dependence Trend and Multivariate Overall Trend tests as proposed by Goutali and Chebana (2024), as well as a plotting function that proves useful as a summary and complement of the tests. Although many packages and methods carry univariate tests, the Mann-Kendall and Spearman's rho test implementations are included in the package with an adapted version to hydrological formulation (e.g. as in Rao and Hamed 1998 <doi:10.1016/S0022-1694(97)00125-X> or Chebana 2022 <doi:10.1016/C2021-0-01317-1>). For better understanding of the example use of the functions, three datasets are included. These are synthetic data and shouldn't be used beyond that purpose.

This package implements Gibbs sampling and Bayes factors for multinomial models with linear inequality constraints on the vector of probability parameters. As special cases, the model class includes models that predict a linear order of binomial probabilities (e.g., p[1] < p[2] < p[3] < .50) and mixture models assuming that the parameter vector p must be inside the convex hull of a finite number of predicted patterns (i.e., vertices). A formal definition of inequality-constrained multinomial models and the implemented computational methods is provided in: Heck, D.W., & Davis-Stober, C.P. (2019). Multinomial models with linear inequality constraints: Overview and improvements of computational methods for Bayesian inference. Journal of Mathematical Psychology, 91, 70-87. <doi:10.1016/j.jmp.2019.03.004>. Inequality-constrained multinomial models have applications in the area of judgment and decision making to fit and test random utility models (Regenwetter, M., Dana, J., & Davis-Stober, C.P. (2011). Transitivity of preferences. Psychological Review, 118, 42â 56, <doi:10.1037/a0021150>) or to perform outcome-based strategy classification to select the decision strategy that provides the best account for a vector of observed choice frequencies (Heck, D.W., Hilbig, B.E., & Moshagen, M. (2017). From information processing to decisions: Formalizing and comparing probabilistic choice models. Cognitive Psychology, 96, 26â 40. <doi:10.1016/j.cogpsych.2017.05.003>).

This package provides tools for likelihood-based inference in one-dimensional stochastic differential equations with mixed effects using expectationâ maximization (EM) algorithms. The package supports Wiener and Ornsteinâ Uhlenbeck diffusion processes with user-specified drift functions, allowing flexible parametric forms including polynomial, exponential, and trigonometric structures. Estimation is performed via Markov chain Monte Carlo EM.

Mask ranges based on expert knowledge or remote sensing layers. These tools can be combined to quantitatively and reproducibly generate a new map or to update an existing map. Methods include expert opinion and data-driven tools to generate thresholds for binary masks.

This package provides tools to conduct Bayesian multivariate network meta-analysis providing - the single correlation coefficient model by Efthimiou et al. (2015) <doi:10.1093/biostatistics/kxu030>; - per-outcome consistency checks using the node-splitting method (Dias et al., 2010) <doi:10.1002/sim.3767>; - per-outcome treatment hierarchies using the surface under the cumulative ranking curve (SUCRA), the probability of best value, or median (or mean) ranks (Salanti et al., 2011) <doi:10.1016/j.jclinepi.2010.03.016>; - across-outcomes benefit-risk assessment using the ViÅ¡eKriterijumska Optimizacija I Kompromisno ReÅ¡enje (VIKOR) method (Opricovic & Tzeng, 2004) <doi:10.1016/S0377-2217(03)00020-1>; - convergence checks using trace plots, density plots, or the R-hat statistic; - forest plots of treatment estimates and consistency checks, scatter plots of per-outcome rankings, Hasse diagrams (Carlsen & Bruggemann, 2014) <doi:10.1002/cem.2569> to visualize the partial order of the treatments across all outcomes.

This package provides a function for measuring the difference between two independent or non-independent empirical distributions and returning a significance level of the difference.

We implement functions allowing for mediation analysis to be performed in cases where the mediator is a count variable with excess zeroes. First a function is provided allowing users to perform analysis for zero-inflated count variables using the marginalized zero-inflated Poisson (MZIP) model (Long et al. 2014 <DOI:10.1002/sim.6293>). Using the counterfactual approach to mediation and MZIP we can obtain natural direct and indirect effects for the overall population. Using delta method processes variance estimation can be performed instantaneously. Alternatively, bootstrap standard errors can be used. We also provide functions for cases with exposure-mediator interactions with four-way decomposition of total effect.

This package provides a user-friendly way for the analysis of multinomial processing tree (MPT) models (e.g., Riefer, D. M., and Batchelder, W. H. [1988]. Multinomial modeling and the measurement of cognitive processes. Psychological Review, 95, 318-339) for single and multiple datasets. The main functions perform model fitting and model selection. Model selection can be done using AIC, BIC, or the Fisher Information Approximation (FIA) a measure based on the Minimum Description Length (MDL) framework. The model and restrictions can be specified in external files or within an R script in an intuitive syntax or using the context-free language for MPTs. The classical .EQN file format for model files is also supported. Besides MPTs, this package can fit a wide variety of other cognitive models such as SDT models (see fit.model). It also supports multicore fitting and FIA calculation (using the snowfall package), can generate or bootstrap data for simulations, and plot predicted versus observed data.

Facilitates performing matching adjusted indirect comparison (MAIC) analysis where the endpoint of interest is either time-to-event (e.g. overall survival) or binary (e.g. objective tumor response). The method is described by Signorovitch et al (2012) <doi:10.1016/j.jval.2012.05.004>.

Extract textual data from different media channels through its source based on users choice of keywords. These data can be used to perform text analysis to identify patterns in respective media reporting. The media channels used in this package are print media. The data (or news) used are publicly available to consumers.

Implemented are various tests for semi-parametric repeated measures and general MANOVA designs that do neither assume multivariate normality nor covariance homogeneity, i.e., the procedures are applicable for a wide range of general multivariate factorial designs. In addition to asymptotic inference methods, novel bootstrap and permutation approaches are implemented as well. These provide more accurate results in case of small to moderate sample sizes. Furthermore, post-hoc comparisons are provided for the multivariate analyses. Friedrich, S., Konietschke, F. and Pauly, M. (2019) <doi:10.32614/RJ-2019-051>.

Machine learning algorithms have been used for performing single missing data imputation and most recently, multiple imputations. However, this is the first attempt for using automated machine learning algorithms for performing both single and multiple imputation. Automated machine learning is a procedure for fine-tuning the model automatic, performing a random search for a model that results in less error, without overfitting the data. The main idea is to allow the model to set its own parameters for imputing each variable separately instead of setting fixed predefined parameters to impute all variables of the dataset. Using automated machine learning, the package fine-tunes an Elastic Net (default) or Gradient Boosting, Random Forest, Deep Learning, Extreme Gradient Boosting, or Stacked Ensemble machine learning model (from one or a combination of other supported algorithms) for imputing the missing observations. This procedure has been implemented for the first time by this package and is expected to outperform other packages for imputing missing data that do not fine-tune their models. The multiple imputation is implemented via bootstrapping without letting the duplicated observations to harm the cross-validation procedure, which is the way imputed variables are evaluated. Most notably, the package implements automated procedure for handling imputing imbalanced data (class rarity problem), which happens when a factor variable has a level that is far more prevalent than the other(s). This is known to result in biased predictions, hence, biased imputation of missing data. However, the autobalancing procedure ensures that instead of focusing on maximizing accuracy (classification error) in imputing factor variables, a fairer procedure and imputation method is practiced.