Fits by ABC, the parameters of a stochastic process modelling the phylogeny and evolution of a suite of traits following the tree. The user may define an arbitrary Markov process for the trait and phylogeny. Importantly, trait-dependent speciation models are handled and fitted to data. See K. Bartoszek, P. Lio (2019) <doi:10.5506/APhysPolBSupp.12.25>. The suggested geiger package can be obtained from CRAN's archive <https://cran.r-project.org/src/contrib/Archive/geiger/>, suggested to take latest version. Otherwise its required code is present in the pcmabc package. The suggested distory package can be obtained from CRAN's archive <https://cran.r-project.org/src/contrib/Archive/distory/>, suggested to take latest version.

This package implements a spatiotemporal boundary detection model with a dissimilarity metric for areal data with inference in a Bayesian setting using Markov chain Monte Carlo (MCMC). The response variable can be modeled as Gaussian (no nugget), probit or Tobit link and spatial correlation is introduced at each time point through a conditional autoregressive (CAR) prior. Temporal correlation is introduced through a hierarchical structure and can be specified as exponential or first-order autoregressive. Full details of the package can be found in the accompanying vignette. Furthermore, the details of the package can be found in "Diagnosing Glaucoma Progression with Visual Field Data Using a Spatiotemporal Boundary Detection Method", by Berchuck et al (2019) <doi:10.1080/01621459.2018.1537911>.

This package provides a differential abundance analysis for the comparison of two or more conditions. Useful for analyzing data from standard RNA-seq or meta-RNA-seq assays as well as selected and unselected values from in-vitro sequence selections. Uses a Dirichlet-multinomial model to infer abundance from counts, optimized for three or more experimental replicates. The method infers biological and sampling variation to calculate the expected false discovery rate, given the variation, based on a Wilcoxon Rank Sum test and Welch's t-test, a Kruskal-Wallis test, a generalized linear model, or a correlation test. All tests report p-values and Benjamini-Hochberg corrected p-values. ALDEx2 also calculates expected standardized effect sizes for paired or unpaired study designs.

Estimating and analyzing auto regressive integrated moving average (ARIMA) models. The primary function in this package is arima(), which fits an ARIMA model to univariate time series data using a random restart algorithm. This approach frequently leads to models that have model likelihood greater than or equal to that of the likelihood obtained by fitting the same model using the arima() function from the stats package. This package enables proper optimization of model likelihoods, which is a necessary condition for performing likelihood ratio tests. This package relies heavily on the source code of the arima() function of the stats package. For more information, please see Jesse Wheeler and Edward L. Ionides (2025) <doi:10.1371/journal.pone.0333993>.

Broadly useful convenient and efficient R functions that bring users concise and elegant R data analyses. This package includes easy-to-use functions for (1) basic R programming (e.g., set working directory to the path of currently opened file; import/export data from/to files in any format; print tables to Microsoft Word); (2) multivariate computation (e.g., compute scale sums/means/... with reverse scoring); (3) reliability analyses and factor analyses; (4) descriptive statistics and correlation analyses; (5) t-test, multi-factor analysis of variance (ANOVA), simple-effect analysis, and post-hoc multiple comparison; (6) tidy report of statistical models (to R Console and Microsoft Word); (7) mediation and moderation analyses (PROCESS); and (8) additional toolbox for statistics and graphics.

Bayesian estimations of a covariance matrix for multivariate normal data. Assumes that the covariance matrix is sparse or band matrix and positive-definite. Methods implemented include the beta-mixture shrinkage prior (Lee et al. (2022) <doi:10.1016/j.jmva.2022.105067>), screened beta-mixture prior (Lee et al. (2024) <doi:10.1214/24-BA1495>), and post-processed posteriors for banded and sparse covariances (Lee et al. (2023) <doi:10.1214/22-BA1333>; Lee and Lee (2023) <doi:10.1016/j.jeconom.2023.105475>). This software has been developed using funding supported by Basic Science Research Program through the National Research Foundation of Korea ('NRF') funded by the Ministry of Education ('RS-2023-00211979', NRF-2022R1A5A7033499', NRF-2020R1A4A1018207 and NRF-2020R1C1C1A01013338').

Supervised learning from a source distribution (with known segmentation into cell sub-populations) to fit a target distribution with unknown segmentation. It relies regularized optimal transport to directly estimate the different cell population proportions from a biological sample characterized with flow cytometry measurements. It is based on the regularized Wasserstein metric to compare cytometry measurements from different samples, thus accounting for possible mis-alignment of a given cell population across sample (due to technical variability from the technology of measurements). Supervised learning technique based on the Wasserstein metric that is used to estimate an optimal re-weighting of class proportions in a mixture model Details are presented in Freulon P, Bigot J and Hejblum BP (2023) <doi:10.1214/22-AOAS1660>.

Inference using a class of Hidden Markov models (HMMs) called oHMMed'(ordered HMM with emission densities <doi:10.1186/s12859-024-05751-4>): The oHMMed algorithms identify the number of comparably homogeneous regions within observed sequences with autocorrelation patterns. These are modelled as discrete hidden states; the observed data points are then realisations of continuous probability distributions with state-specific means that enable ordering of these distributions. The observed sequence is labelled according to the hidden states, permitting only neighbouring states that are also neighbours within the ordering of their associated distributions. The parameters that characterise these state-specific distributions are then inferred. Relevant for application to genomic sequences, time series, or any other sequence data with serial autocorrelation.

This package implements a semi-supervised learning framework for finite mixture models under a mixed-missingness mechanism. The approach models both missing completely at random (MCAR) and entropy-based missing at random (MAR) processes using a logisticâ entropy formulation. Estimation is carried out via an Expectationâ -Conditional Maximisation (ECM) algorithm with robust initialisation routines for stable convergence. The methodology relates to the statistical perspective and informative missingness behaviour discussed in Ahfock and McLachlan (2020) <doi:10.1007/s11222-020-09971-5> and Ahfock and McLachlan (2023) <doi:10.1016/j.ecosta.2022.03.007>. The package provides functions for data simulation, model estimation, prediction, and theoretical Bayes error evaluation for analysing partially labelled data under a mixed-missingness mechanism.

This package provides computational tools for estimating inverse regions and constructing the corresponding simultaneous outer and inner confidence regions. Acceptable input includes both one-dimensional and two-dimensional data for linear, logistic, functional, and spatial generalized least squares regression models. Functions are also available for constructing simultaneous confidence bands (SCBs) for these models. The definition of simultaneous confidence regions (SCRs) follows Sommerfeld et al. (2018) <doi:10.1080/01621459.2017.1341838>. Methods for estimating inverse regions, SCRs, and the nonparametric bootstrap are based on Ren et al. (2024) <doi:10.1093/jrsssc/qlae027>. Methods for constructing SCBs are described in Crainiceanu et al. (2024) <doi:10.1201/9781003278726> and Telschow et al. (2022) <doi:10.1016/j.jspi.2021.05.008>.

This is a package for estimation and inference from generalized linear models based on various methods for bias reduction and maximum penalized likelihood with powers of the Jeffreys prior as penalty. The brglmFit fitting method can achieve reduction of estimation bias by solving either the mean bias-reducing adjusted score equations in Firth (1993) <doi:10.1093/biomet/80.1.27> and Kosmidis and Firth (2009) <doi:10.1093/biomet/asp055>, or the median bias-reduction adjusted score equations in Kenne et al. (2017) <doi:10.1093/biomet/asx046>, or through the direct subtraction of an estimate of the bias of the maximum likelihood estimator from the maximum likelihood estimates as in Cordeiro and McCullagh (1991) <https://www.jstor.org/stable/2345592>.

TaxSEA is an R package for Taxon Set Enrichment Analysis, which utilises a Kolmogorov-Smirnov test analyses to investigate differential abundance analysis output for whether there are alternations in a-priori defined sets of taxa from public databases (BugSigDB, MiMeDB, GutMGene, mBodyMap, BacDive and GMRepoV2) and collated from the literature. TaxSEA takes as input a list of taxonomic identifiers (e.g. species names, NCBI IDs etc.) and a rank (E.g. fold change, correlation coefficient). TaxSEA be applied to any microbiota taxonomic profiling technology (array-based, 16S rRNA gene sequencing, shotgun metagenomics & metatranscriptomics etc.) and enables researchers to rapidly contextualize their findings within the broader literature to accelerate interpretation of results.

Create a blended curve from two survival curves, which is particularly useful for survival extrapolation in health technology assessment. The main idea is to mix a flexible model that fits the observed data well with a parametric model that encodes assumptions about long-term survival. The two curves are blended into a single survival curve that is identical to the first model over the range of observed times and gradually approaches the parametric model over the extrapolation period based on a given weight function. This approach allows for the inclusion of external information, such as data from registries or expert opinion, to guide long-term extrapolations, especially when dealing with immature trial data. See Che et al. (2022) <doi:10.1177/0272989X221134545>.

This package provides the dose transition pathways (DTP) to project in advance the doses recommended by a model-based design for subsequent patients (stay, escalate, deescalate or stop early) using all the accumulated toxicity information; See Yap et al (2017) <doi: 10.1158/1078-0432.CCR-17-0582>. DTP can be used as a design and an operational tool and can be displayed as a table or flow diagram. The dtpcrm package also provides the modified continual reassessment method (CRM) and time-to-event CRM (TITE-CRM) with added practical considerations to allow stopping early when there is sufficient evidence that the lowest dose is too toxic and/or there is a sufficient number of patients dosed at the maximum tolerated dose.

Researchers have been using simulated data from a multivariate linear model to compare and evaluate different methods, ideas and models. Additionally, teachers and educators have been using a simulation tool to demonstrate and teach various statistical and machine learning concepts. This package helps users to simulate linear model data with a wide range of properties by tuning few parameters such as relevant latent components. In addition, a shiny app as an RStudio gadget gives users a simple interface for using the simulation function. See more on: Sæbø, S., Almøy, T., Helland, I.S. (2015) <doi:10.1016/j.chemolab.2015.05.012> and Rimal, R., Almøy, T., Sæbø, S. (2018) <doi:10.1016/j.chemolab.2018.02.009>.

This function produces empirical best linier unbiased predictions (EBLUPs) for Zero-Inflated data and its Relative Standard Error. Small Area Estimation with Zero-Inflated Model (SAE-ZIP) is a model developed for Zero-Inflated data that can lead us to overdispersion situation. To handle this kind of situation, this model is created. The model in this package is based on Small Area Estimation with Zero-Inflated Poisson model proposed by Dian Christien Arisona (2018)<https://repository.ipb.ac.id/handle/123456789/92308>. For the data sample itself, we use combination method between Roberto Benavent and Domingo Morales (2015)<doi:10.1016/j.csda.2015.07.013> and Sabine Krieg, Harm Jan Boonstra and Marc Smeets (2016)<doi:10.1515/jos-2016-0051>.

Used in testing if the indirect effect from linear regression mediation analysis is equal to 0. Includes established methods such as the Sobel Test, Joint Significant test (maxP), and tests based off the distribution of the Product or Normal Random Variables. Additionally, this package adds more powerful tests based on Intersection-Union theory. These tests are the S-Test, the ps-test, and the ascending squares test. These new methods are uniformly more powerful than maxP, which is more powerful than Sobel and less anti-conservative than the Product of Normal Random Variables. These methods are explored by Kidd and Lin, (2024) <doi:10.1007/s12561-023-09386-6> and Kidd et al., (2025) <doi:10.1007/s10260-024-00777-7>.

Analysis of multivariate data with two-way completely randomized factorial design. The analysis is based on fully nonparametric, rank-based methods and uses test statistics based on the Dempster's ANOVA, Wilk's Lambda, Lawley-Hotelling and Bartlett-Nanda-Pillai criteria. The multivariate response is allowed to be ordinal, quantitative, binary or a mixture of the different variable types. The package offers two functions performing the analysis, one for small and the other for large sample sizes. The underlying methodology is largely described in Bathke and Harrar (2016) <doi:10.1007/978-3-319-39065-9_7> and in Munzel and Brunner (2000) <doi:10.1016/S0378-3758(99)00212-8> and in Kiefel and Bathke (2022) <doi:10.1515/stat-2022-0112>.

This package provides a framework for quality-aware analysis of ground-based phenological data from the PEP725 Pan-European Phenology Database (Templ et al. (2018) <doi:10.1007/s00484-018-1512-8>; Templ et al. (2026) <doi:10.1111/nph.70869>) and similar observation networks. Implements station-level data quality grading, outlier detection, phenological normals (climate baselines), anomaly detection, elevation and latitude gradient estimation with robust regression, spatial synchrony quantification, partial least squares (PLS) regression for identifying temperature-sensitive periods, and sequential Mann-Kendall trend analysis. Supports data import from PEP725 files, conversion of user-supplied data, and downloadable synthetic datasets for teaching without barriers of registration. All analysis outputs provide print', summary', and plot methods. Interactive spatial visualization is available via leaflet'.

Computation of t-year survival probabilities and t-year risks with right censored survival data. The Kaplan-Meier estimator is used to provide estimates for data without competing risks and the Aalen-Johansen estimator is used when there are competing risks. Confidence intervals and p-values are obtained using either usual Wald-type inference or empirical likelihood inference, as described in Thomas and Grunkemeier (1975) <doi:10.1080/01621459.1975.10480315> and Blanche (2020) <doi:10.1007/s10985-018-09458-6>. Functions for both one-sample and two-sample inference are provided. Unlike Wald-type inference, empirical likelihood inference always leads to consistent conclusions, in terms of statistical significance, when comparing two risks (or survival probabilities) via either a ratio or a difference.

Component-wise gradient boosting for analysis of multiply imputed datasets. Implements the algorithm Boosting after Multiple Imputation (MIBoost), which enforces uniform variable selection across imputations and provides utilities for pooling. Includes a cross-validation workflow that first splits the data into training and validation sets and then performs imputation on the training data, applying the learned imputation models to the validation data to avoid information leakage. Supports Gaussian and logistic loss. Methods relate to gradient boosting and multiple imputation as in Buehlmann and Hothorn (2007) <doi:10.1214/07-STS242>, Friedman (2001) <doi:10.1214/aos/1013203451>, and van Buuren (2018, ISBN:9781138588318) and Groothuis-Oudshoorn (2011) <doi:10.18637/jss.v045.i03>; see also Kuchen (2025) <doi:10.48550/arXiv.2507.21807>.

Commonly used classification and regression tree methods like the CART algorithm are recursive partitioning methods that build the model in a forward stepwise search. Although this approach is known to be an efficient heuristic, the results of recursive tree methods are only locally optimal, as splits are chosen to maximize homogeneity at the next step only. An alternative way to search over the parameter space of trees is to use global optimization methods like evolutionary algorithms. The evtree package implements an evolutionary algorithm for learning globally optimal classification and regression trees in R. CPU and memory-intensive tasks are fully computed in C++ while the partykit package is leveraged to represent the resulting trees in R, providing unified infrastructure for summaries, visualizations, and predictions.

This package implements the Exploratory Graph Analysis (EGA) framework for dimensionality and psychometric assessment. EGA estimates the number of dimensions in psychological data using network estimation methods and community detection algorithms. A bootstrap method is provided to assess the stability of dimensions and items. Fit is evaluated using the Entropy Fit family of indices. Unique Variable Analysis evaluates the extent to which items are locally dependent (or redundant). Network loadings provide similar information to factor loadings and can be used to compute network scores. A bootstrap and permutation approach are available to assess configural and metric invariance. Hierarchical structures can be detected using Hierarchical EGA. Time series and intensive longitudinal data can be analyzed using Dynamic EGA, supporting individual, group, and population level assessments.

Generates efficient balanced mixed-level k-circulant supersaturated designs by interchanging the elements of the generator vector. Attempts to generate a supersaturated design that has EfNOD efficiency more than user specified efficiency level (mef). Displays the progress of generation of an efficient mixed-level k-circulant design through a progress bar. The progress of 100 per cent means that one full round of interchange is completed. More than one full round (typically 4-5 rounds) of interchange may be required for larger designs. For more details, please see Mandal, B.N., Gupta V. K. and Parsad, R. (2011). Construction of Efficient Mixed-Level k-Circulant Supersaturated Designs, Journal of Statistical Theory and Practice, 5:4, 627-648, <doi:10.1080/15598608.2011.10483735>.