Supervised learning techniques designed for the situation when the dimensionality exceeds the sample size have a tendency to overfit as the dimensionality of the data increases. To remedy this High dimensionality; low sample size (HDLSS) situation, we attempt to learn a lower-dimensional representation of the data before learning a classifier. That is, we project the data to a situation where the dimensionality is more manageable, and then are able to better apply standard classification or clustering techniques since we will have fewer dimensions to overfit. A number of previous works have focused on how to strategically reduce dimensionality in the unsupervised case, yet in the supervised HDLSS regime, few works have attempted to devise dimensionality reduction techniques that leverage the labels associated with the data. In this package and the associated manuscript Vogelstein et al. (2017) <arXiv:1709.01233>, we provide several methods for feature extraction, some utilizing labels and some not, along with easily extensible utilities to simplify cross-validative efforts to identify the best feature extraction method. Additionally, we include a series of adaptable benchmark simulations to serve as a standard for future investigative efforts into supervised HDLSS. Finally, we produce a comprehensive comparison of the included algorithms across a range of benchmark simulations and real data applications.

This package provides a collection of parametric and nonparametric methods for the analysis of survival data. Parametric families implemented include Gompertz-Makeham, exponential and generalized Pareto models and extended models. The package includes an implementation of the nonparametric maximum likelihood estimator for arbitrary truncation and censoring pattern based on Turnbull (1976) <doi:10.1111/j.2517-6161.1976.tb01597.x>, along with graphical goodness-of-fit diagnostics. Parametric models for positive random variables and peaks over threshold models based on extreme value theory are described in Rootzén and Zholud (2017) <doi:10.1007/s10687-017-0305-5>; Belzile et al. (2021) <doi:10.1098/rsos.202097> and Belzile et al. (2022) <doi:10.1146/annurev-statistics-040120-025426>.

Change-point detection algorithm with label constraints and a penalty for each change outside of labels. Read TD Hocking, A Srivastava (2023) <doi:10.1007/s00180-022-01238-z> for details.

Allows the simultaneous analysis of responses and response times in an Item Response Theory (IRT) modelling framework. Supports variable person speed functions (intercept, trend, quadratic), and covariates for item and person (random) parameters. Data missing-by-design can be specified. Parameter estimation is done with a MCMC algorithm. LNIRT replaces the package CIRT, which was written by Rinke Klein Entink. For reference, see the paper by Fox, Klein Entink and Van der Linden (2007), "Modeling of Responses and Response Times with the Package cirt", Journal of Statistical Software, <doi:10.18637/jss.v020.i07>.

Transforms away factors with many levels prior to doing an OLS. Useful for estimating linear models with multiple group fixed effects, and for estimating linear models which uses factors with many levels as pure control variables. See Gaure (2013) <doi:10.1016/j.csda.2013.03.024> Includes support for instrumental variables, conditional F statistics for weak instruments, robust and multi-way clustered standard errors, as well as limited mobility bias correction (Gaure 2014 <doi:10.1002/sta4.68>). Since version 3.0, it provides dedicated functions to estimate Poisson models.

Designed to query Longitudinal Employer-Household Dynamics (LEHD) workplace/residential association and origin-destination flat files and optionally aggregate Census block-level data to block group, tract, county, or state. Data comes from the LODES FTP server <https://lehd.ces.census.gov/data/lodes/LODES8/>.

This package provides a graph proposed by Rosenbaum is useful for checking some properties of various sorts of latent scale, this program generates commands to obtain the graph using dot from graphviz'.

Providing a method for Local Discrimination via Latent Class Models. The approach is described in <https://www.r-project.org/conferences/useR-2009/abstracts/pdf/Bucker.pdf>.

This package provides three classes: Queue, PriorityQueue and Stack. Queue is just a "plain vanilla" FIFO queue; PriorityQueue orders items according to priority. Stack implements LIFO.

Non-parametric prediction of survival outcomes for mixture data that incorporates covariates and a landmark time. Details are described in Garcia (2021) <doi:10.1093/biostatistics/kxz052>.

R lists, especially nested lists, can be very difficult to visualize or represent. Sometimes str() is not enough, so this suite of htmlwidgets is designed to help see, understand, and maybe even modify your R lists. The function reactjson() requires a package reactR that can be installed from CRAN or <https://github.com/timelyportfolio/reactR>.

Linear ridge regression coefficient's estimation and testing with different ridge related measures such as MSE, R-squared etc. REFERENCES i. Hoerl and Kennard (1970) <doi:10.1080/00401706.1970.10488634>, ii. Halawa and El-Bassiouni (2000) <doi:10.1080/00949650008812006>, iii. Imdadullah, Aslam, and Saima (2017), iv. Marquardt (1970) <doi:10.2307/1267205>.

Simulation and estimation of univariate and multivariate log-GARCH models. The main functions of the package are: lgarchSim(), mlgarchSim(), lgarch() and mlgarch(). The first two functions simulate from a univariate and a multivariate log-GARCH model, respectively, whereas the latter two estimate a univariate and multivariate log-GARCH model, respectively.

This package implements methods for analyzing latent variable models with measurement error correction, including Item Response Theory (IRT) models. Provides tools for various correction methods such as Bayesian Markov Chain Monte Carlo (MCMC), over-imputation, bootstrapping for robust standard errors, Ordinary Least Squares (OLS), and Instrumental Variables (IV) based approaches. Supports flexible specification of observable indicators and groupings for latent variable analyses in social sciences and other fields. Methods are described in a working paper (2025) <doi:10.48550/arXiv.2507.22218>.

Conveniently generate CSS using R code.

Supervised classification methods, which (if asked) can provide step-by-step explanations of the algorithms used, as described in PK Josephine et. al., (2021) <doi:10.59176/kjcs.v1i1.1259>; and datasets to test them on, which highlight the strengths and weaknesses of each technique.

This package provides regularized structural equation modeling (regularized SEM) with non-smooth penalty functions (e.g., lasso) building on lavaan'. The package is heavily inspired by the ['regsem'](<https://github.com/Rjacobucci/regsem>) and ['lslx'](<https://github.com/psyphh/lslx>) packages.

Computational routines for estimating local Gaussian parameters. Local Gaussian parameters are useful for characterizing and testing for non-linear dependence within bivariate data. See e.g. Tjostheim and Hufthammer, Local Gaussian correlation: A new measure of dependence, Journal of Econometrics, 2013, Volume 172 (1), pages 33-48 <DOI:10.1016/j.jeconom.2012.08.001>.

Publication-ready regional gene locus plots similar to those produced by the web interface LocusZoom <https://my.locuszoom.org>, but running locally in R. Genetic or genomic data with gene annotation tracks are plotted via R base graphics, ggplot2 or plotly', allowing flexibility and easy customisation including laying out multiple locus plots on the same page. It uses the LDlink API <https://ldlink.nih.gov/?tab=apiaccess> to query linkage disequilibrium data from the 1000 Genomes Project and can overlay this on plots <doi:10.1093/bioadv/vbaf006>.

This package provides functions for summarizing, visualizing, and analyzing Likert-scale survey data. Includes support for computing descriptive statistics, Relative Importance Index (RII), reliability analysis (Cronbach's Alpha), and response distribution plots.

This package contains functions to estimate a penalized regression model using 3CoSE algorithm, see Weber, Striaukas, Schumacher Binder (2018) <doi:10.2139/ssrn.3211163>.

Automatically returns 24 logistic models including 13 individual models and 11 ensembles of models of logistic data. The package also returns 25 plots, 5 tables, and a summary report. The package automatically builds all 24 models, reports all results, and provides graphics to show how the models performed. This can be used for a wide range of data, such as sports or medical data. The package includes medical data (the Pima Indians data set), and information about the performance of Lebron James. The package can be used to analyze many other examples, such as stock market data. The package automatically returns many values for each model, such as True Positive Rate, True Negative Rate, False Positive Rate, False Negative Rate, Positive Predictive Value, Negative Predictive Value, F1 Score, Area Under the Curve. The package also returns 36 Receiver Operating Characteristic (ROC) curves for each of the 24 models.

This package implements the LPC method of Witten&Tibshirani(Annals of Applied Statistics 2008) for identification of significant genes in a microarray experiment.

This package provides tools for model specification in the latent variable framework (add-on to the lava package). The package contains three main functionalities: Wald tests/F-tests with improved control of the type 1 error in small samples, adjustment for multiple comparisons when searching for local dependencies, and adjustment for multiple comparisons when doing inference for multiple latent variable models.