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).

Likelihood evaluations for stationary Gaussian time series are typically obtained via the Durbin-Levinson algorithm, which scales as O(n^2) in the number of time series observations. This package provides a "superfast" O(n log^2 n) algorithm written in C++, crossing over with Durbin-Levinson around n = 300. Efficient implementations of the score and Hessian functions are also provided, leading to superfast versions of inference algorithms such as Newton-Raphson and Hamiltonian Monte Carlo. The C++ code provides a Toeplitz matrix class packaged as a header-only library, to simplify low-level usage in other packages and outside of R.

This package provides a set of functions to calculate sample size for two-sample difference in means tests. Does adjustments for either nonadherence or variability that comes from using data to estimate parameters.

The Robots Exclusion Protocol <https://www.robotstxt.org/orig.html> documents a set of standards for allowing or excluding robot/spider crawling of different areas of site content. Tools are provided which wrap The rep-cpp <https://github.com/seomoz/rep-cpp> C++ library for processing these robots.txt files.

Non-proportional hazard (NPH) is commonly observed in immuno-oncology studies, where the survival curves of the treatment and control groups show delayed separation. To properly account for NPH, several statistical methods have been developed. One such method is Max-Combo test, which is a straightforward and flexible hypothesis testing method that can simultaneously test for constant, early, middle, and late treatment effects. However, the majority of the Max-Combo test performed in clinical studies are unstratified, ignoring the important prognostic stratification factors. To fill this gap, we have developed an R package for stratified Max-Combo testing that accounts for stratified baseline factors. Our package explores various methods for calculating combined test statistics, estimating joint distributions, and determining the p-values.

Settings and functions to extend the knitr Stata engine.

Econometric estimation of simultaneous systems of linear and nonlinear equations using Ordinary Least Squares (OLS), Weighted Least Squares (WLS), Seemingly Unrelated Regressions (SUR), Two-Stage Least Squares (2SLS), Weighted Two-Stage Least Squares (W2SLS), and Three-Stage Least Squares (3SLS) as suggested, e.g., by Zellner (1962) <doi:10.2307/2281644>, Zellner and Theil (1962) <doi:10.2307/1911287>, and Schmidt (1990) <doi:10.1016/0304-4076(90)90127-F>.

This package implements a suite of semiparametric and nonparametric kernel-smoothed estimation and testing procedures for continuous mark-specific stratified hazard ratio (treatment/placebo) models in a randomized treatment efficacy trial with a time-to-event endpoint. Semiparametric methods, allowing multivariate marks, are described in Juraska M and Gilbert PB (2013), Mark-specific hazard ratio model with multivariate continuous marks: an application to vaccine efficacy. Biometrics 69(2):328-337 <doi:10.1111/biom.12016>, and in Juraska M and Gilbert PB (2016), Mark-specific hazard ratio model with missing multivariate marks. Lifetime Data Analysis 22(4):606-25 <doi:10.1007/s10985-015-9353-9>. Nonparametric kernel-smoothed methods, allowing univariate marks only, are described in Sun Y and Gilbert PB (2012), Estimation of stratified markâ specific proportional hazards models with missing marks. Scandinavian Journal of Statistics

Stochastic frontier analysis with advanced methods. In particular, it applies the approach proposed by Latruffe et al. (2017) <DOI:10.1093/ajae/aaw077> to estimate a stochastic frontier with technical inefficiency effects when one input is endogenous.

This package provides a collection of helper functions for forming bootstrapping confidence intervals and examining bootstrap estimates in structural equation modelling. Currently supports models fitted by the lavaan package by Rosseel (2012) <doi: 10.18637/jss.v048.i02>.

Identifies single nucleotide variants in next-generation sequencing data by estimating their local false discovery rates. For more details, see Karimnezhad, A. and Perkins, T. J. (2024) <doi:10.1038/s41598-024-51958-z>.

One key exploratory analysis step in single-cell genomics data analysis is the prediction of features with different activity levels. For example, we want to predict differentially expressed genes (DEGs) in single-cell RNA-seq data, spatial DEGs in spatial transcriptomics data, or differentially accessible regions (DARs) in single-cell ATAC-seq data. singleCellHaystack predicts differentially active features in single cell omics datasets without relying on the clustering of cells into arbitrary clusters. singleCellHaystack uses Kullback-Leibler divergence to find features (e.g., genes, genomic regions, etc) that are active in subsets of cells that are non-randomly positioned inside an input space (such as 1D trajectories, 2D tissue sections, multi-dimensional embeddings, etc). For the theoretical background of singleCellHaystack we refer to our original paper Vandenbon and Diez (Nature Communications, 2020) <doi:10.1038/s41467-020-17900-3> and our update Vandenbon and Diez (Scientific Reports, 2023) <doi:10.1038/s41598-023-38965-2>.

Simulation methods for the Fisher Bingham distribution on the unit sphere, the matrix Bingham distribution on a Grassmann manifold, the matrix Fisher distribution on SO(3), and the bivariate von Mises sine model on the torus. The methods use an acceptance/rejection simulation algorithm for the Bingham distribution and are described fully by Kent, Ganeiber and Mardia (2018) <doi:10.1080/10618600.2017.1390468>. These methods supersede earlier MCMC simulation methods and are more general than earlier simulation methods. The methods can be slower in specific situations where there are existing non-MCMC simulation methods (see Section 8 of Kent, Ganeiber and Mardia (2018) <doi:10.1080/10618600.2017.1390468> for further details).

Compute relative or absolute population trends across space and time using predictions from models fitted to ecological population abundance data, as described in Knape (2025) <doi:10.1016/j.ecolind.2025.113435>. The package supports models fitted by mgcv or brms', and draws from posterior predictive distributions.

This statistical method uses the nearest neighbor algorithm to estimate absolute distances between single cells based on a chosen constellation of surface proteins, with these distances being a measure of the similarity between the two cells being compared. Based on Sen, N., Mukherjee, G., and Arvin, A.M. (2015) <DOI:10.1016/j.ymeth.2015.07.008>.

This package provides estimation of simultaneous bootstrap and asymptotic confidence intervals for diversity indices, namely the Shannon and the Simpson index. Several pre--specified multiple comparison types are available to choose. Further user--defined contrast matrices are applicable. In addition, simboot estimates adjusted as well as unadjusted p--values for two of the three proposed bootstrap methods. Further simboot allows for comparing biological diversities of two or more groups while simultaneously testing a user-defined selection of Hill numbers of orders q, which are considered as appropriate and useful indices for measuring diversity.

Data sets utilized by the SGP package as exemplars for users to conduct their own student growth percentiles (SGP) analyses.

Deals with Young tableaux (field of combinatorics). For standard Young tabeaux, performs enumeration, counting, random generation, the Robinson-Schensted correspondence, and conversion to and from paths on the Young lattice. Also performs enumeration and counting of semistandard Young tableaux, enumeration of skew semistandard Young tableaux, enumeration of Gelfand-Tsetlin patterns, and computation of Kostka numbers.

This package provides tools for obtaining, processing, and visualizing spectral reflectance data for the user-defined land or water surface classes for visual exploring in which wavelength the classes differ. Input should be a shapefile with polygons of surface classes (it might be different habitat types, crops, vegetation, etc.). The Sentinel-2 L2A satellite mission optical bands pixel data are obtained through the Google Earth Engine service (<https://earthengine.google.com/>) and used as a source of spectral data.

Diagnostics for fixed effects linear and general linear regression models fitted with survey data. Extensions of standard diagnostics to complex survey data are included: standardized residuals, leverages, Cook's D, dfbetas, dffits, condition indexes, and variance inflation factors as found in Li and Valliant (Surv. Meth., 2009, 35(1), pp. 15-24; Jnl. of Off. Stat., 2011, 27(1), pp. 99-119; Jnl. of Off. Stat., 2015, 31(1), pp. 61-75); Liao and Valliant (Surv. Meth., 2012, 38(1), pp. 53-62; Surv. Meth., 2012, 38(2), pp. 189-202). Variance inflation factors and condition indexes are also computed for some general linear models as described in Liao (U. Maryland thesis, 2010).

Optimal hard thresholding of singular values. The procedure adaptively estimates the best singular value threshold under unknown noise characteristics. The threshold chosen by ScreeNOT is optimal (asymptotically, in the sense of minimum Frobenius error) under the the so-called "Spiked model" of a low-rank matrix observed in additive noise. In contrast to previous works, the noise is not assumed to be i.i.d. or white; it can have an essentially arbitrary and unknown correlation structure, across either rows, columns or both. ScreeNOT is proposed to practitioners as a mathematically solid alternative to Cattell's ever-popular but vague Scree Plot heuristic from 1966. If you use this package, please cite our paper: David L. Donoho, Matan Gavish and Elad Romanov (2023). "ScreeNOT: Exact MSE-optimal singular value thresholding in correlated noise." Annals of Statistics, 2023 (To appear). <arXiv:2009.12297>.

The implementation to perform the geometric spatial point analysis developed in Hernández & Solàs (2022) <doi:10.1007/s00180-022-01244-1>. It estimates the geometric goodness-of-fit index for a set of variables against a response one based on the sf package. The package has methods to print and plot the results.

Connecting to databases requires boilerplate code to specify connection parameters and to set up sessions properly with the DBMS. This package provides a simple tool to fill two purposes: abstracting connection details, including secret credentials, out of your source code and managing configuration for frequently-used database connections in a persistent and flexible way, while minimizing requirements on the runtime environment.

This package provides pseudo-likelihood methods for empirically analyzing common signaling games in international relations as described in Crisman-Cox and Gibilisco (2019) <doi:10.1017/psrm.2019.58>.