Tests for equality of two survival functions based on integrated weighted differences of two Kaplan-Meier curves.

This package creates ggplot2'-based visualizations of smooth effects from GAM (Generalized Additive Models) fitted with mgcv and spline effects from GLM (Generalized Linear Models). Supports survey-weighted models ('svyglm', svycoxph') from the survey package, interaction terms, and provides hazard ratio plots with histograms for survival analysis. Wood (2017, ISBN:9781498728331) provides comprehensive methodology for generalized additive models.

Wraps the classifier from the Sundararajan (2021) <doi:10.1038/s41598-020-79217-x> to estimate sleep using a random forest. Users must download the model files from Sundararajan (2020) <doi:10.5281/zenodo.3752645> in order to use this method.

Computes the entire regularization path for the two-class svm classifier with essentially the same cost as a single SVM fit.

This package contains more modern tools for causal inference using regression standardization. Four general classes of models are implemented; generalized linear models, conditional generalized estimating equation models, Cox proportional hazards models, and shared frailty gamma-Weibull models. Methodological details are described in Sjölander, A. (2016) <doi:10.1007/s10654-016-0157-3>. Also includes functionality for doubly robust estimation for generalized linear models in some special cases, and the ability to implement custom models.

This package produces various measures of expected treatment effect heterogeneity under an assumption of homogeneity across subgroups. Graphical presentations are created to compare these expected differences with the observed differences.

This package provides a computational framework for identification of B cell clones from Adaptive Immune Receptor Repertoire sequencing (AIRR-Seq) data. Three main functions are included (identicalClones, hierarchicalClones, and spectralClones) that perform clustering among sequences of BCRs/IGs (B cell receptors/immunoglobulins) which share the same V gene, J gene and junction length. Nouri N and Kleinstein SH (2018) <doi: 10.1093/bioinformatics/bty235>. Nouri N and Kleinstein SH (2019) <doi: 10.1101/788620>. Gupta NT, et al. (2017) <doi: 10.4049/jimmunol.1601850>.

Apply the spectral residual algorithm to data, such as a time series, to detect anomalies. Anomaly scores can be used to determine outliers based upon a threshold or fed into more sophisticated prediction models. Methods are based upon "Time-Series Anomaly Detection Service at Microsoft", Ren, H., Xu, B., Wang, Y., et al., (2019) <doi:10.48550/arXiv.1906.03821>.

Sparsity Oriented Importance Learning (SOIL) provides a new variable importance measure for high dimensional linear regression and logistic regression from a sparse penalization perspective, by taking into account the variable selection uncertainty via the use of a sensible model weighting. The package is an implementation of Ye, C., Yang, Y., and Yang, Y. (2017+).

Sample Generation by Replacement simulations (SGR; Lombardi & Pastore, 2014; Pastore & Lombardi, 2014). The package can be used to perform fake data analysis according to the sample generation by replacement approach. It includes functions for making simple inferences about discrete/ordinal fake data. The package allows to study the implications of fake data for empirical results.

Adds support for the English language to the sylly package. To ask for help, report bugs, suggest feature improvements, or discuss the global development of the package, please consider subscribing to the koRpus-dev mailing list (<https://korpusml.reaktanz.de>).

This package implements survival-model-based imputation for censored laboratory measurements, including Tobit-type models with several distribution options. Suitable for data with values below detection or quantification limits, the package identifies the best-fitting distribution and produces realistic imputations that respect the censoring thresholds.

Perform association test within linear mixed model framework using score test integrated with Empirical Bayes for genome-wide association study. Firstly, score test was conducted for each marker under linear mixed model framework, taking into account the genetic relatedness and population structure. And then all the potentially associated markers were selected with a less stringent criterion. Finally, all the selected markers were placed into a multi-locus model to identify the true quantitative trait nucleotide.

This package creates simulated data from structural equation models with standardized loading. Data generation methods are described in Schneider (2013) <doi:10.1177/0734282913478046>.

Pathway Analysis is statistically linking observations on the molecular level to biological processes or pathways on the systems(i.e., organism, organ, tissue, cell) level. Traditionally, pathway analysis methods regard pathways as collections of single genes and treat all genes in a pathway as equally informative. However, this can lead to identifying spurious pathways as statistically significant since components are often shared amongst pathways. SIGORA seeks to avoid this pitfall by focusing on genes or gene pairs that are (as a combination) specific to a single pathway. In relying on such pathway gene-pair signatures (Pathway-GPS), SIGORA inherently uses the status of other genes in the experimental context to identify the most relevant pathways. The current version allows for pathway analysis of human and mouse datasets. In addition, it contains pre-computed Pathway-GPS data for pathways in the KEGG and Reactome pathway repositories and mechanisms for extracting GPS for user-supplied repositories.

This package implements a two-stage Bayesian hierarchical modeling framework for applying shrinkage to subgroup-specific effects. The package separates model fitting (Stage 1) from hierarchical shrinkage (Stage 2), enabling modular sensitivity analyses without refitting expensive Markov chain Monte Carlo (MCMC) chains. Supports flexible prior specifications through the distributional package, mixture approximations via mclust', and efficient Stan'-based inference.

Build interactive user interfaces for shiny applications through a conversation with a large language model (LLM). Developers choose a set of reusable components, and the model arranges and updates those components as the user describes what they need. Each component's inputs are checked before it is shown, and the model supplies data rather than executable code. Applications can also save and replay the sequence of interface changes without contacting a model. For background on generative user interfaces, see Leviathan et al. (2026) <doi:10.48550/arXiv.2604.09577>.

Handles both vector and matrices, using a flexible S4 class for automatic differentiation. The method used is forward automatic differentiation. Many functions and methods have been defined, so that in most cases, functions written without automatic differentiation in mind can be used without change.

Models with skewâ normally distributed and thus asymmetric error terms, implementing the methods developed in Badunenko and Henderson (2023) "Production analysis with asymmetric noise" <doi:10.1007/s11123-023-00680-5>. The package provides tools to estimate regression models with skewâ normal error terms, allowing both the variance and skewness parameters to be heteroskedastic. It also includes a stochastic frontier framework that accommodates both i.i.d. and heteroskedastic inefficiency terms.

Copula based Cox proportional hazards models for survival data subject to dependent censoring. This approach does not assume that the parameter defining the copula is known. The dependency parameter is estimated with other finite model parameters by maximizing a Pseudo likelihood function. The cumulative hazard function is estimated via estimating equations derived based on martingale ideas. Available copula functions include Frank, Gumbel and Normal copulas. Only Weibull and lognormal models are allowed for the censoring model, even though any parametric model that satisfies certain identifiability conditions could be used. Implemented methods are described in the article "Copula based Cox proportional hazards models for dependent censoring" by Deresa and Van Keilegom (2024) <doi:10.1080/01621459.2022.2161387>.

An extension of the AlphaSimR package (<https://cran.r-project.org/package=AlphaSimR>) for stochastic simulations of honeybee populations and breeding programmes. SIMplyBee enables simulation of individual bees that form a colony, which includes a queen, fathers (drones the queen mated with), virgin queens, workers, and drones. Multiple colony can be merged into a population of colonies, such as an apiary or a whole country of colonies. Functions enable operations on castes, colony, or colonies, to ease R scripting of whole populations. All AlphaSimR functionality with respect to genomes and genetic and phenotype values is available and further extended for honeybees, including haplo-diploidy, complementary sex determiner locus, colony events (swarming, supersedure, etc.), and colony phenotype values.

It can be useful to temporarily hide some text or other HTML elements in Shiny applications. Building on Spoiler-Alert.js', it is possible to select the elements to hide at startup, to partially reveal them by hovering them, and to completely show them when clicking on them.

Standard RGB spaces included are sRGB, Adobe RGB, ProPhoto RGB, BT.709, and others. User-defined RGB spaces are also possible. There is partial support for ACES Color workflows.

This package provides a statistical learning method to simultaneously predict a range of target phenotypes using codified and natural language processing (NLP)-derived Electronic Health Record (EHR) data. See Ahuja et al (2020) JAMIA <doi:10.1093/jamia/ocaa079> for details.