Algorithms of distance-based k-medoids clustering: simple and fast k-medoids, ranked k-medoids, and increasing number of clusters in k-medoids. Calculate distances for mixed variable data such as Gower, Podani, Wishart, Huang, Harikumar-PV, and Ahmad-Dey. Cluster validation applies internal and relative criteria. The internal criteria includes silhouette index and shadow values. The relative criterium applies bootstrap procedure producing a heatmap with a flexible reordering matrix algorithm such as complete, ward, or average linkages. The cluster result can be plotted in a marked barplot or pca biplot.

In the context of multistate models, which are popular in sociology, demography, and epidemiology, Markov chain with rewards calculations can help to refine transition timings and so obtain more accurate estimates. The package code accommodates up to nine transient states and irregular age (time) intervals. Traditional demographic life tables result as a special case. Formulas and methods involved are explained in detail in the accompanying article: Schneider / Myrskyla / van Raalte (2021): Flexible Transition Timing in Discrete-Time Multistate Life Tables Using Markov Chains with Rewards, MPIDR Working Paper WP-2021-002.

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.

Some accelerated three-term conjugate gradient algorithms implemented purely in R with the same user interface as optim(). The search directions and acceleration scheme are described in Andrei, N. (2013) <doi:10.1016/j.amc.2012.11.097>, Andrei, N. (2013) <doi:10.1016/j.cam.2012.10.002>, and Andrei, N (2015) <doi:10.1007/s11075-014-9845-9>. Line search is done by a hybrid algorithm incorporating the ideas in Oliveia and Takahashi (2020) <doi:10.1145/3423597> and More and Thuente (1994) <doi:10.1145/192115.192132>.

This package contains functions for calculating under-five child mortality estimates using the Trussell version of the Brass method (United Nations (1990) <https://www.un.org/en/development/desa/population/publications/pdf/mortality/stepguide_childmort.pdf> and United Nations (1983) <https://www.un.org/en/development/desa/population/publications/pdf/mortality/stepguide_childmort.pdf>) as well as applying the cohort-derived methods by Rajaratnam and colleagues (Rajaratnam JK, Tran LN, Lopez AD, Murray CJL (2010) "Measuring Under-Five Mortality: Validation of New Low-Cost Methods" <doi:10.1371/journal.pmed.1000253>).

TSIS is used for detecting transcript isoform switches in time-series data. Transcript isoform switches occur when a pair of alternatively spliced isoforms reverse the order of their relative expression levels. TSIS characterizes the transcript switch by defining the isoform switch time-points for any pair of transcript isoforms within a gene. In addition, this tool describes the switch using five different features or metrics. Also it filters the results with user’s specifications and visualizes the results using different plots for the user to examine further details of the switches.

Users can estimate the treatment effect for multiple subgroups basket trials based on the Bayesian Cluster Hierarchical Model (BCHM). In this model, a Bayesian non-parametric method is applied to dynamically calculate the number of clusters by conducting the multiple cluster classification based on subgroup outcomes. Hierarchical model is used to compute the posterior probability of treatment effect with the borrowing strength determined by the Bayesian non-parametric clustering and the similarities between subgroups. To use this package, JAGS software and rjags package are required, and users need to pre-install them.

When samples contain missing data, are small, or are suspected of bias, estimation of scale reliability may not be trustworthy. A recommended solution for this common problem has been Bayesian model estimation. Bayesian methods rely on user specified information from historical data or researcher intuition to more accurately estimate the parameters. This package provides a user friendly interface for estimating test reliability. Here, reliability is modeled as a beta distributed random variable with shape parameters alpha=true score variance and beta=error variance (Tanzer & Harlow, 2020) <doi:10.1080/00273171.2020.1854082>.

Analyzes non-verbal communication by processing data extracted from video recordings of dyadic interactions. It supports integration with open source tools, currently limited to OpenPose (Cao et al. (2019) <doi:10.1109/TPAMI.2019.2929257>), converting its outputs into CSV format for further analysis. The package includes functions for data pre-processing, visualization, and computation of motion indices such as velocity, acceleration, and jerkiness (Cook et al. (2013) <doi:10.1093/brain/awt208>), facilitating the analysis of non-verbal cues in paired interactions and contributing to research on human communication dynamics.

Extends the Changes-in-Changes model a la Athey and Imbens (2006) <doi:10.1111/j.1468-0262.2006.00668.x> to multiple cohorts and time periods, which generalizes difference-in-differences estimation techniques to the entire distribution. Computes quantile treatment effects for every possible two-by-two combination in ecic(). Then, aggregating all bootstrap runs adds the standard errors in summary_ecic(). Results can be plotted with plot_ecic() aggregated over all cohort-group combinations or in an event-study style for either individual periods or individual quantiles.

The functions provided in the FADA (Factor Adjusted Discriminant Analysis) package aim at performing supervised classification of high-dimensional and correlated profiles. The procedure combines a decorrelation step based on a factor modeling of the dependence among covariates and a classification method. The available methods are Lasso regularized logistic model (see Friedman et al. (2010)), sparse linear discriminant analysis (see Clemmensen et al. (2011)), shrinkage linear and diagonal discriminant analysis (see M. Ahdesmaki et al. (2010)). More methods of classification can be used on the decorrelated data provided by the package FADA.

This package provides a weighting approach that employs kernels to make one group have a similar distribution to another group on covariates. This method matches not only means or marginal distributions but also higher-order transformations implied by the choice of kernel. kbal is applicable to both treatment effect estimation and survey reweighting problems. Based on Hazlett, C. (2020) "Kernel Balancing: A flexible non-parametric weighting procedure for estimating causal effects." Statistica Sinica. <https://www.researchgate.net/publication/299013953_Kernel_Balancing_A_flexible_non-parametric_weighting_procedure_for_estimating_causal_effects/stats>.

Distance metrics for mixed-type data consisting of continuous, nominal, and ordinal variables. This methodology uses additive and product kernels to calculate similarity functions and metrics, and selects variables relevant to the underlying distance through bandwidth selection via maximum similarity cross-validation. These methods can be used in any distance-based algorithm, such as distance-based clustering. For further details, we refer the reader to Ghashti and Thompson (2024) <doi:10.1007/s00357-024-09493-z> for dkps() methodology, and Ghashti (2024) <doi:10.14288/1.0443975> for dkss() methodology.

This package provides a variety of functions for the best known and most innovative approaches to nonparametric boundary estimation. The selected methods are concerned with empirical, smoothed, unrestricted as well as constrained fits under both separate and multiple shape constraints. They cover robust approaches to outliers as well as data envelopment techniques based on piecewise polynomials, splines, local linear fitting, extreme values and kernel smoothing. The package also seamlessly allows for Monte Carlo comparisons among these different estimation methods. Its use is illustrated via a number of empirical applications and simulated examples.

The Open Bodem Index (OBI) is a method to evaluate the quality of soils of agricultural fields in The Netherlands and the sustainability of the current agricultural practices. The OBI score is based on four main criteria: chemical, physical, biological and management, which consist of more than 21 indicators. By providing results of a soil analysis and management info the OBIC package can be use to calculate he scores, indicators and derivatives that are used by the OBI. More information about the Open Bodem Index can be found at <https://openbodemindex.nl/>.

The queueing model of visual search models the accuracy and response time data in a visual search experiment using queueing models with finite customer population and stopping criteria of completing the service for finite number of customers. It implements the conceptualization of a hybrid model proposed by Moore and Wolfe (2001), in which visual stimuli enter the processing one after the other and then are identified in parallel. This package provides functions that simulate the specified queueing process and calculate the Wasserstein distance between the empirical response times and the model prediction.

REDUCE is a portable general-purpose computer algebra system. It is a system for doing scalar, vector and matrix algebra by computer, which also supports arbitrary precision numerical approximation and interfaces to gnuplot to provide graphics. It can be used interactively for simple calculations but also provides a full programming language, with a syntax similar to other modern programming languages. REDUCE supports alternative user interfaces including Run-REDUCE, TeXmacs and GNU Emacs. This package provides the Codemist Standard Lisp (CSL) version of REDUCE. It uses the gnuplot program, if installed, to draw figures.

Four methods for mediation analysis with missing data: Listwise deletion, Pairwise deletion, Multiple imputation, and Two Stage Maximum Likelihood algorithm. For MI and TS-ML, auxiliary variables can be included. Bootstrap confidence intervals for mediation effects are obtained. The robust method is also implemented for TS-ML. Since version 1.4, bmem adds the capability to conduct power analysis for mediation models. Details about the methods used can be found in these articles. Zhang and Wang (2003) <doi:10.1007/s11336-012-9301-5>. Zhang (2014) <doi:10.3758/s13428-013-0424-0>.

Multivariable fractional polynomial algorithm simultaneously selects variables and functional forms in both generalized linear models and Cox proportional hazard models. Key references for this algorithm are Royston and Altman (1994)<doi:10.2307/2986270> and Sauerbrei and Royston (2008, ISBN:978-0-470-02842-1). In addition, it can model a sigmoid relationship between variable x and an outcome variable y using the approximate cumulative distribution transformation proposed by Royston (2014) <doi:10.1177/1536867X1401400206>. This feature distinguishes it from a standard fractional polynomial function, which lacks the ability to achieve such modeling.

Calculation of Predictive Moran's eigenvector maps (pMEM), as defined by Guénard and Legendre (In Press) "Spatially-explicit predictions using spatial eigenvector maps" <doi:10.5281/zenodo.13356457>. Methods in Ecology and Evolution. This method enables scientists to predict the values of spatially-structured environmental variables. Multiple types of pMEM are defined, each one implemented on the basis of spatial weighting function taking a range parameter, and sometimes also a shape parameter. The code's modular nature enables programers to implement new pMEM by defining new spatial weighting functions.

Implement a GAM-based (Generalized Additive Models) spatial surplus production model (spatial SPM), aimed at modeling northern shrimp population in Atlantic Canada but potentially to any stock in any location. The package is opinionated in its implementation of SPMs as it internally makes the choice to use penalized spatial gams with time lags. However, it also aims to provide options for the user to customize their model. The methods are described in Pedersen et al. (2022, <https://www.dfo-mpo.gc.ca/csas-sccs/Publications/ResDocs-DocRech/2022/2022_062-eng.html>).

Monte Carlo and MCMC sampling algorithms for semiparametric Bayesian regression analysis. These models feature a nonparametric (unknown) transformation of the data paired with widely-used regression models including linear regression, spline regression, quantile regression, and Gaussian processes. The transformation enables broader applicability of these key models, including for real-valued, positive, and compactly-supported data with challenging distributional features. The samplers prioritize computational scalability and, for most cases, Monte Carlo (not MCMC) sampling for greater efficiency. Details of the methods and algorithms are provided in Kowal and Wu (2023) <arXiv:2306.05498>.

This package provides a collection of procedures for analysing, visualising, and managing single-case data. These include piecewise linear regression models, multilevel models, overlap indices ('PND', PEM', PAND', PET', tau-u', baseline corrected tau', CDC'), and randomization tests. Data preparation functions support outlier detection, handling missing values, scaling, and custom transformations. An export function helps to generate html, word, and latex tables in a publication friendly style. More details can be found in the online book Analyzing single-case data with R and scan', Juergen Wilbert (2025) <https://jazznbass.github.io/scan-Book/>.

We provide functionality to implement penalized PCA with an option to smooth the objective function using Nesterov smoothing. Two functions are available to compute a user-specified number of eigenvectors. The function unsmoothed_penalized_EV() computes a penalized PCA without smoothing and has three parameters (the input matrix, the Lasso penalty, and the number of desired eigenvectors). The function smoothed_penalized_EV() computes a smoothed penalized PCA using the same parameters and additionally requires the specification of a smoothing parameter. Both functions return a matrix having the desired eigenvectors as columns.