Curated datasets and intuitive data management functions to streamline epidemiological data workflows. It is designed to support researchers in quickly accessing clean, structured data and applying essential cleaning, summarizing, visualization, and export operations with minimal effort. Whether you're preparing a cohort for analysis or creating reports, DIVINE makes the process more efficient, transparent, and reproducible.

An R package for iterative and batched record linkage, and applying epidemiological case definitions. diyar can be used for deterministic and probabilistic record linkage, or multistage record linkage combining both approaches. It features the implementation of nested match criteria, and mechanisms to address missing data and conflicting matches during stepwise record linkage. Case definitions are implemented by assigning records to groups based on match criteria such as person or place, and overlapping time or duration of events e.g. sample collection dates or periods of hospital stays. Matching records are assigned a unique group ID. Index and duplicate records are removed or further analyses as required.

Diagnostic and prognostic models are typically evaluated with measures of accuracy that do not address clinical consequences. Decision-analytic techniques allow assessment of clinical outcomes, but often require collection of additional information may be cumbersome to apply to models that yield a continuous result. Decision curve analysis is a method for evaluating and comparing prediction models that incorporates clinical consequences, requires only the data set on which the models are tested, and can be applied to models that have either continuous or dichotomous results. See the following references for details on the methods: Vickers (2006) <doi:10.1177/0272989X06295361>, Vickers (2008) <doi:10.1186/1472-6947-8-53>, and Pfeiffer (2020) <doi:10.1002/bimj.201800240>.

This package performs differential network analysis to infer disease specific gene networks.

Differential Item Functioning (DIF) Analysis with shiny application interfaces. You can run the functions in this package without any arguments and perform your DIF analysis using user-friendly interfaces.

Simulation models (apps) of various within-host immune response scenarios. The purpose of the package is to help individuals learn about within-host infection and immune response modeling from a dynamical systems perspective. All apps include explanations of the underlying models and instructions on what to do with the models.

Computes dynamical correlation estimates and percentile bootstrap confidence intervals for pairs of longitudinal responses, including consideration of lags and derivatives.

Using the Theory of Belief Functions for evidence calculus. Basic probability assignments, or mass functions, can be defined on the subsets of a set of possible values and combined. A mass function can be extended to a larger frame. Marginalization, i.e. reduction to a smaller frame can also be done. These features can be combined to analyze small belief networks and take into account situations where information cannot be satisfactorily described by probability distributions.

Implementation of three methods based on the diversity forest (DF) algorithm (Hornung, 2022, <doi:10.1007/s42979-021-00920-1>), a split-finding approach that enables complex split procedures in random forests. The package includes: 1. Interaction forests (IFs) (Hornung & Boulesteix, 2022, <doi:10.1016/j.csda.2022.107460>): Model quantitative and qualitative interaction effects using bivariable splitting. Come with the Effect Importance Measure (EIM), which can be used to identify variable pairs that have well-interpretable quantitative and qualitative interaction effects with high predictive relevance. 2. Two random forest-based variable importance measures (VIMs) for multi-class outcomes: the class-focused VIM, which ranks covariates by their ability to distinguish individual outcome classes from the others, and the discriminatory VIM, which measures overall covariate influence irrespective of class-specific relevance. 3. The basic form of diversity forests that uses conventional univariable, binary splitting (Hornung, 2022). Except for the multi-class VIMs, all methods support categorical, metric, and survival outcomes. The package includes visualization tools for interpreting the identified covariate effects. Built as a fork of the ranger R package (main author: Marvin N. Wright), which implements random forests using an efficient C++ implementation.

This package provides a library of density, distribution function, quantile function, (bounded) raw moments and random generation for a collection of distributions relevant for the firm size literature. Additionally, the package contains tools to fit these distributions using maximum likelihood and evaluate these distributions based on (i) log-likelihood ratio and (ii) deviations between the empirical and parametrically implied moments of the distributions. We add flexibility by allowing the considered distributions to be combined into piecewise composite or finite mixture distributions, as well as to be used when truncated. See Dewitte (2020) <https://hdl.handle.net/1854/LU-8644700> for a description and application of methods available in this package.

This package implements a flexible, versatile, and computationally tractable model for density regression based on a single-weights dependent Dirichlet process mixture of normal distributions model for univariate continuous responses. The model assumes an additive structure for the mean of each mixture component and the effects of continuous covariates are captured through smooth nonlinear functions. The key components of our modelling approach are penalised B-splines and their bivariate tensor product extension. The proposed method can also easily deal with parametric effects of categorical covariates, linear effects of continuous covariates, interactions between categorical and/or continuous covariates, varying coefficient terms, and random effects. Please see Rodriguez-Alvarez, Inacio et al. (2025) for more details.

This package provides a system for the management, assessment, and psychometric analysis of data from educational and psychological tests.

This package provides an implementation of a mixture of hidden Markov models (HMMs) for discrete sequence data in the Discrete Bayesian HMM Clustering (DBHC) algorithm. The DBHC algorithm is an HMM Clustering algorithm that finds a mixture of discrete-output HMMs while using heuristics based on Bayesian Information Criterion (BIC) to search for the optimal number of HMM states and the optimal number of clusters.

This package provides functions for (1) ranking, selecting, and prioritising genes, proteins, and metabolites from high dimensional biology experiments, (2) multivariate hit calling in high content screens, and (3) combining data from diverse sources.

An R interface to the codediff JavaScript library (a copy of which is included in the package, see <https://github.com/danvk/codediff.js> for information). Allows for visualization of the difference between 2 files, usually text files or R scripts, in a browser.

We provide three distance metrics for measuring the separation between two clusters in high-dimensional spaces. The first metric is the centroid distance, which calculates the Euclidean distance between the centers of the two groups. The second is a ridge Mahalanobis distance, which incorporates a ridge correction constant, alpha, to ensure that the covariance matrix is invertible. The third metric is the maximal data piling distance, which computes the orthogonal distance between the affine spaces spanned by each class. These three distances are asymptotically interconnected and are applicable in tasks such as discrimination, clustering, and outlier detection in high-dimensional settings.

Geologic pattern data from <https://ngmdb.usgs.gov/fgdc_gds/geolsymstd.php>. Access functions are provided in the accompanying package deeptime'.

Cancer genomes contain large numbers of somatic alterations but few genes drive tumor development. Identifying cancer driver genes is critical for precision oncology. Most of current approaches either identify driver genes based on mutational recurrence or using estimated scores predicting the functional consequences of mutations. driveR is a tool for personalized or batch analysis of genomic data for driver gene prioritization by combining genomic information and prior biological knowledge. As features, driveR uses coding impact metaprediction scores, non-coding impact scores, somatic copy number alteration scores, hotspot gene/double-hit gene condition, phenolyzer gene scores and memberships to cancer-related KEGG pathways. It uses these features to estimate cancer-type-specific probability for each gene of being a cancer driver using the related task of a multi-task learning classification model. The method is described in detail in Ulgen E, Sezerman OU. 2021. driveR: driveR: a novel method for prioritizing cancer driver genes using somatic genomics data. BMC Bioinformatics <doi:10.1186/s12859-021-04203-7>.

This package provides mean squared error (MSE) and plot the kernel densities related to extreme value distributions with their estimated values. By using Gumbel and Weibull Kernel. See Salha et al. (2014) <doi:10.4236/ojs.2014.48061> and Khan and Akbar (2021) <doi:10.4236/ojs.2021.112018 >.

Construction and analysis of matrix population models in R.

This package provides utilities to calculate the probabilities of various dice-rolling events, such as the probability of rolling a four-sided die six times and getting a 4, a 3, and either a 1 or 2 among the six rolls (in any order); the probability of rolling two six-sided dice three times and getting a 10 on the first roll, followed by a 4 on the second roll, followed by anything but a 7 on the third roll; or the probabilities of each possible sum of rolling five six-sided dice, dropping the lowest two rolls, and summing the remaining dice.

Piecewise linear segmentation of ordered data by a dynamic programming algorithm. The algorithm was developed for time series data, e.g. growth curves, and for genome-wide read-count data from next generation sequencing, but is broadly applicable. Generic implementations of dynamic programming routines allow to scan for optimal segmentation parameters and test custom segmentation criteria ("scoring functions").

For identifying, estimating, and plotting descriptive multidimensional item response theory models, restricted to 3D and dichotomous or polytomous data that fit the two-parameter logistic model or the graded response model. The method is foremost explorative and centered around the plot function that exposes item characteristics and constructs, represented by vector arrows, located in a three-dimensional interactive latent space. The results can be useful for item-level analysis as well as test development.

Diagnostic classification models are psychometric models used to categorically estimate respondents mastery, or proficiency, on a set of predefined skills (Bradshaw, 2016, <doi:10.1002/9781118956588.ch13>). Diagnostic models can be estimated with Stan'; however, the necessary scripts can be long and complicated. This package automates the creation of Stan scripts for diagnostic classification models. Specify different types of diagnostic models, define prior distributions, and automatically generate the necessary Stan code for estimating the model.