Recursive partitioning methods to build classification trees for ordinal responses within the CART framework. Trees are grown using the Generalized Gini impurity function, where the misclassification costs are given by the absolute or squared differences in scores assigned to the categories of the response. Pruning is based on the total misclassification rate or on the total misclassification cost.

Implementation of the Integrated Simple Weighted Sum Product Method (WISP), a multiple criteria sorting method create by Dragisa Stanujkic (2021) <doi:10.1109/TEM.2021.3075783>.

Resampling Stats (http://www.resample.com) is an add-in for running randomization tests in Excel worksheets. The workflow is (1) to define a statistic of interest that can be calculated from a data table, (2) to randomize rows ad/or columns of a data table to simulate a null hypothesis and (3) and to score the value of the statistic from many randomizations. The relative frequency distribution of the statistic in the simulations is then used to infer the probability of the observed value be generated by the null process (probability of Type I error). This package intends to translate this logic for R for teaching purposes. Keeping the original workflow is favored over performance.

Implementations of several robust nonparametric two-sample tests for location or scale differences. The test statistics are based on robust location and scale estimators, e.g. the sample median or the Hodges-Lehmann estimators as described in Fried & Dehling (2011) <doi:10.1007/s10260-011-0164-1>. The p-values can be computed via the permutation principle, the randomization principle, or by using the asymptotic distributions of the test statistics under the null hypothesis, which ensures (approximate) distribution independence of the test decision. To test for a difference in scale, we apply the tests for location difference to transformed observations; see Fried (2012) <doi:10.1016/j.csda.2011.02.012>. Random noise on a small range can be added to the original observations in order to hold the significance level on data from discrete distributions. The location tests assume homoscedasticity and the scale tests require the location parameters to be zero.

This package provides a lightweight implementation of the geomorphon terrain form classification algorithm of Jasiewicz and Stepinski (2013) <doi:10.1016/j.geomorph.2012.11.005> based largely on the GRASS GIS r.geomorphon module. This implementation employs a novel algorithm written in C++ and RcppParallel'.

Adds menu items to the R Commander for implementing case 1 (object case) best-worst scaling (BWS1) from designing choice sets to measuring preferences for items. BWS1 is a question-based survey method that constructs various combinations of items (choice sets) using the experimental designs, asks respondents to select the best and worst items in each choice set, and then measures preferences for the items by analyzing the responses. For details, refer to Aizaki and Fogarty (2023) <doi:10.1016/j.jocm.2022.100394>.

Test for effects of both individual factors and their interaction on replicated spatial patterns in a two factorial design, as explained in Ramon et al. (2016) <doi:10.1111/ecog.01848>.

This package provides a data mining approach for longitudinal and clustered data, which combines the structure of mixed effects model with tree-based estimation methods. See Sela, R.J. and Simonoff, J.S. (2012) RE-EM trees: a data mining approach for longitudinal and clustered data <doi:10.1007/s10994-011-5258-3>.

Portfolio optimization is achieved through a combination of regularization techniques and ensemble methods that are designed to generate stable out-of-sample return predictions, particularly in the presence of strong correlations among assets. The package includes functions for data preparation, parallel processing, and portfolio analysis using methods such as Mean-Variance, James-Stein, LASSO, Ridge Regression, and Equal Weighting. It also provides visualization tools and performance metrics, such as the Sharpe ratio, volatility, and maximum drawdown, to assess the results.

This package provides a programmatic interface to openfisheries.org'. This package is part of the rOpenSci suite (http://ropensci.org).

Random generation of survival data from a wide range of regression models, including accelerated failure time (AFT), proportional hazards (PH), proportional odds (PO), accelerated hazard (AH), Yang and Prentice (YP), and extended hazard (EH) models. The package rsurv also stands out by its ability to generate survival data from an unlimited number of baseline distributions provided that an implementation of the quantile function of the chosen baseline distribution is available in R. Another nice feature of the package rsurv lies in the fact that linear predictors are specified via a formula-based approach, facilitating the inclusion of categorical variables and interaction terms. The functions implemented in the package rsurv can also be employed to simulate survival data with more complex structures, such as survival data with different types of censoring mechanisms, survival data with cure fraction, survival data with random effects (frailties), multivariate survival data, and competing risks survival data. Details about the R package rsurv can be found in Demarqui (2024) <doi:10.48550/arXiv.2406.01750>.

This package implements robust ratio-cum-product estimators using auxiliary medians for estimating the population mean under simple random sampling without replacement (SRSWOR). Provides analytical optimal tuning parameters, bias, Mean Squared Error (MSE), and Percent Relative Efficiency (PRE) evaluations.

This package provides a very lightweight package that writes out log messages in an opinionated way. Simpler and lighter than other logging packages, rlog provides a compact feature set that focuses on getting the job done in a Unix-like way.

This package performs kernel based estimates on in-memory raster images from the raster package. These kernel estimates include local means variances, modes, and quantiles. All results are in the form of raster images, preserving original resolution and projection attributes.

Implementation of robust sparse PCA using the ROSPCA algorithm of Hubert et al. (2016) <DOI:10.1080/00401706.2015.1093962>.

Assists in the manipulation and processing of linear features with the help of the sf package. Makes use of linear referencing to extract data from most shape files. Reference for this packages methods: Albeke, S.E. et al. (2010) <doi:10.1007/s10980-010-9528-4>.

Interface to JDemetra+ 3.x (<https://github.com/jdemetra>) time series analysis software. It offers full access to txt, csv, xml and spreadsheets files which are meant to be read by JDemetra+ Graphical User Interface.

Routines to interact with the Numerai Machine Learning Tournament API <https://numer.ai>. The functionality includes the ability to automatically download the current tournament data, submit predictions, and to get information for your user.

Using this package, it is possible to call a BUGS model, summarize inferences and convergence in a table and graph, and save the simulations in arrays for easy access in R.

Downloads Southern Oscillation Index, Oceanic Nino Index, North Pacific Gyre Oscillation data, North Atlantic Oscillation and Arctic Oscillation. Data sources are described in the help files for each function.

This package provides a set of functions for receiver operating characteristic (ROC) curve estimation and area under the curve (AUC) calculation. All functions are designed to work with aggregated data; nevertheless, they can also handle raw samples. In ROCket', we distinguish two types of ROC curve representations: 1) parametric curves - the true positive rate (TPR) and the false positive rate (FPR) are functions of a parameter (the score), 2) functions - TPR is a function of FPR. There are several ROC curve estimation methods available. An introduction to the mathematical background of the implemented methods (and much more) can be found in de Zea Bermudez, Gonçalves, Oliveira & Subtil (2014) and Cai & Pepe (2004).

Model relational and durational events in a counting process framework, with functions for estimating and simulating Relational Event Models (REM) and Durational Event Models (DEM). Includes support for time-varying covariates, windowed statistics, and high-dimensional node-level fixed effects. References include Fritz et al. (2026) "Scalable Durational Event Models: Application to Physical and Digital Interactions" <doi:10.48550/arXiv.2504.00049>.

The Radiant Design menu includes interfaces for design of experiments, sampling, and sample size calculation. The application extends the functionality in radiant.data'.

An implementation of robust bent line regression. It can fit the bent line regression and test the existence of change point, for the paper, "Feipeng Zhang and Qunhua Li (2016). Robust bent line regression, submitted.".