Main properties and regression procedures using a generalization of the Dirichlet distribution called Simplicial Generalized Beta distribution. It is a new distribution on the simplex (i.e. on the space of compositions or positive vectors with sum of components equal to 1). The Dirichlet distribution can be constructed from a random vector of independent Gamma variables divided by their sum. The SGB follows the same construction with generalized Gamma instead of Gamma variables. The Dirichlet exponents are supplemented by an overall shape parameter and a vector of scales. The scale vector is itself a composition and can be modeled with auxiliary variables through a log-ratio transformation. Graf, M. (2017, ISBN: 978-84-947240-0-8). See also the vignette enclosed in the package.

Applies re-sampled kernel density method to detect vote fraud. It estimates the proportion of coarse vote-shares in the observed data relative to the null hypothesis of no fraud.

Estimates cohort-by-time average treatment effects under staggered treatment adoption by the generalized method of moments. Three weighting schemes are provided, corresponding to a pooled stationary covariance, a cohort-specific stationary covariance, and an unrestricted within-cohort covariance. Optional adjustment for baseline covariates by outcome regression, and a serial-correlation robust over-identification test of unconditional parallel trends and no anticipation, are also supported. The methods are described in Arora and Bijani (2026) <doi:10.2139/ssrn.6558759>.

Animal movement models including Moving-Resting Process with Embedded Brownian Motion (Yan et al., 2014, <doi:10.1007/s10144-013-0428-8>; Pozdnyakov et al., 2017, <doi:10.1007/s11009-017-9547-6>), Brownian Motion with Measurement Error (Pozdnyakov et al., 2014, <doi:10.1890/13-0532.1>), Moving-Resting-Handling Process with Embedded Brownian Motion (Pozdnyakov et al., 2020, <doi:10.1007/s11009-020-09774-1>), Moving-Resting Process with Measurement Error (Hu et al., 2021, <doi:10.1111/2041-210X.13694>), Moving-Moving Process with two Embedded Brownian Motions.

This is a core implementation of SAS procedures for linear models - GLM, REG, ANOVA, TTEST, FREQ, and UNIVARIATE. Some R packages provide Type II and Type III SS. However, the results of nested and complex designs are often different from those of SAS'. Different results do not necessarily mean incorrectness. However, many want the same results as SAS'. This package aims to achieve that. Reference: Littell RC, Stroup WW, Freund RJ (2002, ISBN:0-471-22174-0).

This package provides some code to run simulations of state-space models, and then use these in the Approximate Bayesian Computation Sequential Monte Carlo (ABC-SMC) algorithm of Toni et al. (2009) <doi:10.1098/rsif.2008.0172> and a bootstrap particle filter based particle Markov chain Monte Carlo (PMCMC) algorithm (Andrieu et al., 2010 <doi:10.1111/j.1467-9868.2009.00736.x>). Also provides functions to plot and summarise the outputs.

Implementation of a shiny app to easily compare supervised machine learning model performances. You provide the data and configure each model parameter directly on the shiny app. Different supervised learning algorithms can be tested either on Spark or H2O frameworks to suit your regression and classification tasks. Implementation of available machine learning models on R has been done by Lantz (2013, ISBN:9781782162148).

Forms likelihood-based confidence intervals (LBCIs) for parameters in structural equation modeling, introduced in Cheung and Pesigan (2023) <doi:10.1080/10705511.2023.2183860>. Currently implements the algorithm illustrated by Pek and Wu (2018) <doi:10.1037/met0000163>, and supports the robust LBCI proposed by Falk (2018) <doi:10.1080/10705511.2017.1367254>.

We propose a novel two-step procedure to combine epidemiological data obtained from diverse sources with the aim to quantify risk factors affecting the probability that an individual develops certain disease such as cancer. See Hui Huang, Xiaomei Ma, Rasmus Waagepetersen, Theodore R. Holford, Rong Wang, Harvey Risch, Lloyd Mueller & Yongtao Guan (2014) A New Estimation Approach for Combining Epidemiological Data From Multiple Sources, Journal of the American Statistical Association, 109:505, 11-23, <doi:10.1080/01621459.2013.870904>.

An input controller for R Shiny: a matrix with radio buttons, where only one option per row can be selected.

Calculate change point based on spectral clustering with the option to automatically calculate the number of clusters if this information is not available.

This package provides tools for transport planning with an emphasis on spatial transport data and non-motorized modes. The package was originally developed to support the Propensity to Cycle Tool', a publicly available strategic cycle network planning tool (Lovelace et al. 2017) <doi:10.5198/jtlu.2016.862>, but has since been extended to support public transport routing and accessibility analysis (Moreno-Monroy et al. 2017) <doi:10.1016/j.jtrangeo.2017.08.012> and routing with locally hosted routing engines such as OSRM (Lowans et al. 2023) <doi:10.1016/j.enconman.2023.117337>. The main functions are for creating and manipulating geographic "desire lines" from origin-destination (OD) data (building on the od package); calculating routes on the transport network locally and via interfaces to routing services such as <https://cyclestreets.net/> (Desjardins et al. 2021) <doi:10.1007/s11116-021-10197-1>; and calculating route segment attributes such as bearing. The package implements the travel flow aggregration method described in Morgan and Lovelace (2020) <doi:10.1177/2399808320942779> and the OD jittering method described in Lovelace et al. (2022) <doi:10.32866/001c.33873>. Further information on the package's aim and scope can be found in the vignettes and in a paper in the R Journal (Lovelace and Ellison 2018) <doi:10.32614/RJ-2018-053>, and in a paper outlining the landscape of open source software for geographic methods in transport planning (Lovelace, 2021) <doi:10.1007/s10109-020-00342-2>.

Non-parametric test, originally proposed by Stute (1997) <https://www.jstor.org/stable/2242560>, that the expectation of a dependent variable Y given an independent variable D is linear in D.

Covariate adjustment for randomized trials using stable balancing weights (SBW), as proposed by Irish, Zubizarreta, and Luedtke (2026) <doi:10.48550/arXiv.2609.01638>. sbw_weights() fits exact-balance SBW for a two-arm study by a closed-form solve with a nonnegative quadratic-programming fallback; sbw_estimate() computes a closed menu of treatment-effect estimands (average treatment effect, relative risk, survival ratio, Mann-Whitney, quantile contrasts) from the fitted weights, with bootstrap confidence intervals.

Soft-margin support vector machines (SVMs) are a common class of classification models. The training of SVMs usually requires that the data be available all at once in a single batch, however the Stochastic majorization-minimization (SMM) algorithm framework allows for the training of SVMs on streamed data instead Nguyen, Jones & McLachlan(2018)<doi:10.1007/s42081-018-0001-y>. This package utilizes the SMM framework to provide functions for training SVMs with hinge loss, squared-hinge loss, and logistic loss.

This package implements a set of distribution modeling methods that are suited to species with small sample sizes (e.g., poorly sampled species or rare species). While these methods can also be used on well-sampled taxa, they are united by the fact that they can be utilized with relatively few data points. More details on the currently implemented methodologies can be found in Maitner et al. (2026) <doi:10.1002/ecog.08112>, Drake and Richards (2018) <doi:10.1002/ecs2.2373>, Drake (2015) <doi:10.1098/rsif.2015.0086>, and Drake (2014) <doi:10.1890/ES13-00202.1>.

Detects spatial and temporal groups in GPS relocations (Robitaille et al. (2019) <doi:10.1111/2041-210X.13215>). It can be used to convert GPS relocations to gambit-of-the-group format to build proximity-based social networks, and perform data-stream randomization methods suitable for GPS data. Also provides measures of intragroup social dynamics including distance and direction to leaders, centroids and nearest neighbours.

This package provides a supervised compression method that incorporates the response for reducing big data to a carefully selected subset. Please see Joseph and Mak (2021) <doi:10.1002/sam.11508>. This research is supported by a U.S. National Science Foundation (NSF) grant CMMI-1921646.

Detects, normalizes, classifies, and extracts scholarly identifier strings. Provides lightweight, dependency-free helpers for identifier types including DOIs, ORCID iDs, ISBNs, ISSNs, arXiv and PubMed identifiers, ROR and ISNI, OpenAlex and ADS bibcodes, RRID, ARK, SWHID, and selected life-science accessions (UniProt, RefSeq, SRA, GEO, BioProject, and genome assemblies). Functions are vectorized, predictable, and suitable as low-level building blocks for other R packages and data workflows. Use scholid_types() for the authoritative type list. For online lookup, conversion, metadata retrieval, and linked identifier discovery, see scholidonline'.

Bayesian spatial models for survey data, such as Demographic and Health Survey (DHS), with spatial cluster location displacement adjustments. The package implements models for (1) continuous, (2) binary, (3) count and (4) spatially varying models for continuous outcomes. For more details see Bakar et al. (2026) <doi:10.1093/jrsssa/qnag068>.

Simple Component Analysis (SCA) often provides much more interpretable components than Principal Components (PCA) while still representing much of the variability in the data.

This package provides functions for simplified emulation of time series computer model output in model parameter space using Gaussian processes. Stilt can be used more generally for Kriging of spatio-temporal fields. There are functions to predict at new parameter settings, to test the emulator using cross-validation (which includes information on 95% confidence interval empirical coverage), and to produce contour plots over 2D slices in model parameter space.

This package implements a test for distinguishing between true long memory and spurious long memory. Reference: Qu, Z. (2011). "A Test Against Spurious Long Memory." Journal of Business & Economic Statistics, 29(3), 423â 438. <doi:10.1198/jbes.2010.09153>.

This package provides the SMOTE with Boosting (SMOTEWB) algorithm. See F. SaÄ lam, M. A. Cengiz (2022) <doi:10.1016/j.eswa.2022.117023>. It is a SMOTE-based resampling technique which creates synthetic data on the links between nearest neighbors. SMOTEWB uses boosting weights to determine where to generate new samples and automatically decides the number of neighbors for each sample. It is robust to noise and outperforms most of the alternatives according to Matthew Correlation Coefficient metric. Alternative resampling methods are also available in the package.