Estimation and regularization for covariance matrix of asset returns. For covariance matrix estimation, three major types of factor models are included: macroeconomic factor model, fundamental factor model and statistical factor model. For covariance matrix regularization, four regularized estimators are included: banding, tapering, hard-thresholding and soft- thresholding. The tuning parameters of these regularized estimators are selected via cross-validation.

Lognormal models have broad applications in various research areas such as economics, actuarial science, biology, environmental science and psychology. The estimation problem in lognormal models has been extensively studied. This R package fuel implements thirty-nine existing and newly proposed estimators. See Zhang, F., and Gou, J. (2020), A unified framework for estimation in lognormal models, Technical report.

Used for the design and analysis of a 2x2 factorial trial for a time-to-event endpoint. It performs power calculations and significance testing as well as providing estimates of the relevant hazard ratios and the corresponding 95% confidence intervals. Important reference papers include Slud EV. (1994) <https://www.ncbi.nlm.nih.gov/pubmed/8086609> Lin DY, Gong J, Gallo P, Bunn PH, Couper D. (2016) <DOI:10.1111/biom.12507> Leifer ES, Troendle JF, Kolecki A, Follmann DA. (2020) <https://github.com/EricSLeifer/factorial2x2/blob/master/Leifer%20et%20al.%20paper.pdf>.

This package performs backward elimination with similar syntax to the stepAIC() function from the MASS package. A bounding algorithm is used to avoid fitting unnecessary models, making it much faster.

Offers calculation, visualization and comparison of algorithmic fairness metrics. Fair machine learning is an emerging topic with the overarching aim to critically assess whether ML algorithms reinforce existing social biases. Unfair algorithms can propagate such biases and produce predictions with a disparate impact on various sensitive groups of individuals (defined by sex, gender, ethnicity, religion, income, socioeconomic status, physical or mental disabilities). Fair algorithms possess the underlying foundation that these groups should be treated similarly or have similar prediction outcomes. The fairness R package offers the calculation and comparisons of commonly and less commonly used fairness metrics in population subgroups. These methods are described by Calders and Verwer (2010) <doi:10.1007/s10618-010-0190-x>, Chouldechova (2017) <doi:10.1089/big.2016.0047>, Feldman et al. (2015) <doi:10.1145/2783258.2783311> , Friedler et al. (2018) <doi:10.1145/3287560.3287589> and Zafar et al. (2017) <doi:10.1145/3038912.3052660>. The package also offers convenient visualizations to help understand fairness metrics.

Constructs optimal policy trees which provide a rule-based treatment prescription policy. Input is covariate and reward data, where, typically, the rewards will be doubly robust reward estimates. This package aims to construct optimal policy trees more quickly than the existing policytree package and is intended to be used alongside that package. For more details see Cussens, Hatamyar, Shah and Kreif (2025) <doi:10.48550/arXiv.2506.15435>.

This package provides a comprehensive set of datasets and tools for causal inference research. The package includes data from clinical trials, cancer studies, epidemiological surveys, environmental exposures, and health-related observational studies. Designed to facilitate causal analysis, risk assessment, and advanced statistical modeling, it leverages datasets from packages such as causalOT', survival', causalPAF', evident', melt', and sanon'. The package is inspired by the foundational work of Pearl (2009) <doi:10.1017/CBO9780511803161> on causal inference frameworks.

This package provides a collection of functions for linear and non-linear regression modelling. It implements a wrapper for several regression models available in the base and contributed packages of R.

This package provides an efficient C++ code for computing an optimal segmentation model with Poisson loss, up-down constraints, and label constraints, as described by Kaufman et al. (2024) <doi:10.1080/10618600.2023.2293216>.

This package provides the probability density function (PDF), cumulative distribution function (CDF), the first-order and second-order partial derivatives of the PDF, and a fitting function for the diffusion decision model (DDM; e.g., Ratcliff & McKoon, 2008, <doi:10.1162/neco.2008.12-06-420>) with across-trial variability in the drift rate. Because the PDF, its partial derivatives, and the CDF of the DDM both contain an infinite sum, they need to be approximated. fddm implements all published approximations (Navarro & Fuss, 2009, <doi:10.1016/j.jmp.2009.02.003>; Gondan, Blurton, & Kesselmeier, 2014, <doi:10.1016/j.jmp.2014.05.002>; Blurton, Kesselmeier, & Gondan, 2017, <doi:10.1016/j.jmp.2016.11.003>; Hartmann & Klauer, 2021, <doi:10.1016/j.jmp.2021.102550>) plus new approximations. All approximations are implemented purely in C++ providing faster speed than existing packages.

Fuel economy data from the EPA, 1985-2015, conveniently packaged for consumption by R users.

Wrapper functions that interface with Freesurfer <https://surfer.nmr.mgh.harvard.edu/>, a powerful and commonly-used neuroimaging software, using system commands. The goal is to be able to interface with Freesurfer completely in R, where you pass R objects of class nifti', implemented by package oro.nifti', and the function executes an Freesurfer command and returns an R object of class nifti or necessary output.

This package provides a replacement for dplyr::na_if(). Allows you to specify multiple values to be replaced with NA using a single function.

This is an extremely fast implementation of a Naive Bayes classifier. This package is currently the only package that supports a Bernoulli distribution, a Multinomial distribution, and a Gaussian distribution, making it suitable for both binary features, frequency counts, and numerical features. Another feature is the support of a mix of different event models. Only numerical variables are allowed, however, categorical variables can be transformed into dummies and used with the Bernoulli distribution. The implementation is largely based on the paper "A comparison of event models for Naive Bayes anti-spam e-mail filtering" written by K.M. Schneider (2003) <doi:10.3115/1067807.1067848>. Any issues can be submitted to: <https://github.com/mskogholt/fastNaiveBayes/issues>.

Supports teaching methods of estimating and testing time series factor models for use in robust portfolio construction and analysis. Unique in providing not only classical least squares, but also modern robust model fitting methods which are not much influenced by outliers. Includes returns and risk decompositions, with user choice of standard deviation, value-at-risk, and expected shortfall risk measures. "Robust Statistics Theory and Methods (with R)", R. A. Maronna, R. D. Martin, V. J. Yohai, M. Salibian-Barrera (2019) <doi:10.1002/9781119214656>.

Three methods are implemented in R to facilitate the aggregations of flags in official statistics. From the underlying flags the highest in the hierarchy, the most frequent, or with the highest total weight is propagated to the flag(s) for EU or other aggregates. Below there are some reference documents for the topic: <https://sdmx.org/wp-content/uploads/CL_OBS_STATUS_v2_1.docx>, <https://sdmx.org/wp-content/uploads/CL_CONF_STATUS_1_2_2018.docx>, <http://ec.europa.eu/eurostat/data/database/information>, <http://www.oecd.org/sdd/33869551.pdf>, <https://sdmx.org/wp-content/uploads/CL_OBS_STATUS_implementation_20-10-2014.pdf>.

Useful tools for conveniently downloading FHIR resources in xml format and converting them to R data.frames. The package uses FHIR-search to download bundles from a FHIR server, provides functions to save and read xml-files containing such bundles and allows flattening the bundles to data.frames using XPath expressions. FHIR® is the registered trademark of HL7 and is used with the permission of HL7. Use of the FHIR trademark does not constitute endorsement of this product by HL7.

The aim of the package is to provide some basic functions for doing statistics with trapezoidal fuzzy numbers. In particular, the package contains several functions for simulating trapezoidal fuzzy numbers, as well as for calculating some central tendency measures (mean and two types of median), some scale measures (variance, ADD, MDD, Sn, Qn, Tn and some M-estimators) and one diversity index and one inequality index. Moreover, functions for calculating the 1-norm distance, the mid/spr distance and the (phi,theta)-wabl/ldev/rdev distance between fuzzy numbers are included, and a function to calculate the value phi-wabl given a sample of trapezoidal fuzzy numbers.

Enables filtering datasets by a prior specified identifiers which correspond to saved filter expressions.

This package provides a wide variety of tools for general data analysis, wrangling, spelling, statistics, visualizations, package development, and more. All functions have vectorized implementations whenever possible. Exported names are designed to be readable, with longer names possessing short aliases.

Convenient functions for ensemble forecasts in R combining approaches from the forecast package. Forecasts generated from auto.arima(), ets(), thetaf(), nnetar(), stlm(), tbats(), snaive() and arfima() can be combined with equal weights, weights based on in-sample errors (introduced by Bates & Granger (1969) <doi:10.1057/jors.1969.103>), or cross-validated weights. Cross validation for time series data with user-supplied models and forecasting functions is also supported to evaluate model accuracy.

Integrate Item Response Theory (IRT) and Federated Learning to estimate traditional IRT models, including the 2-Parameter Logistic (2PL) and the Graded Response Models, with enhanced privacy. It allows for the estimation in a distributed manner without compromising accuracy. A user-friendly shiny application is included.

Impute general multivariate missing data with the fractional hot deck imputation based on Jaekwang Kim (2011) <doi:10.1093/biomet/asq073>.

This package provides tools, helpers and data structures for developing models and time series functions for fable and extension packages. These tools support a consistent and tidy interface for time series modelling and analysis.