Risk-related information (like the prevalence of conditions, the sensitivity and specificity of diagnostic tests, or the effectiveness of interventions or treatments) can be expressed in terms of frequencies or probabilities. By providing a toolbox of corresponding metrics and representations, riskyr computes, translates, and visualizes risk-related information in a variety of ways. Adopting multiple complementary perspectives provides insights into the interplay between key parameters and renders teaching and training programs on risk literacy more transparent (see <doi:10.3389/fpsyg.2020.567817>, for details).

Relative, generalized, and Erreygers corrected concentration index; plot Lorenz curves; and decompose health inequalities into contributing factors. The package currently works with (generalized) linear models, survival models, complex survey models, and marginal effects probit models. originally forked by Brecht Devleesschauwer from the decomp package (no longer on CRAN), rineq is now maintained by Kaspar Walter Meili. Compared to the earlier rineq version on github by Brecht Devleesschauwer (<https://github.com/brechtdv/rineq>), the regression tree functionality has been removed. Improvements compared to earlier versions include improved plotting of decomposition and concentration, added functionality to calculate the concentration index with different methods, calculation of robust standard errors, and support for the decomposition analysis using marginal effects probit regression models. The development version is available at <https://github.com/kdevkdev/rineq>.

This package provides a lightweight toolkit to validate new observations when computing their predictions with a predictive model. The validation process consists of two steps: (1) record relevant statistics and meta data of the variables in the original training data for the predictive model and (2) use these data to run a set of basic validation tests on the new set of observations.

This package performs joint selection in Generalized Linear Mixed Models (GLMMs) using penalized likelihood methods. Specifically, the Penalized Quasi-Likelihood (PQL) is used as a loss function, and penalties are then augmented to perform simultaneous fixed and random effects selection. Regularized PQL avoids the need for integration (or approximations such as the Laplace's method) during the estimation process, and so the full solution path for model selection can be constructed relatively quickly.

This package provides a tool designed to analyze recurrent events when dealing with right-censored data and the potential presence of a terminal event (that prevents further occurrences, like death). It extends the random survival forest algorithm, adapting splitting rules and node estimators to handle complexities of recurrent events. The methodology is fully described in Murris, J., Bouaziz, O., Jakubczak, M., Katsahian, S., & Lavenu, A. (2024) (<https://hal.science/hal-04612431v1/document>).

This framework aims to provide classes and methods for manipulating and processing of raster time series data (e.g. a time series of satellite images).

Sequential permutation testing for statistical significance of predictors in random forests and other prediction methods. The main function of the package is rfvimptest(), which allows to test for the statistical significance of predictors in random forests using different (sequential) permutation test strategies [1]. The advantage of sequential over conventional permutation tests is that they are computationally considerably less intensive, as the sequential procedure is stopped as soon as there is sufficient evidence for either the null or the alternative hypothesis. Reference: [1] Hapfelmeier, A., Hornung, R. & Haller, B. (2023) Efficient permutation testing of variable importance measures by the example of random forests. Computational Statistics & Data Analysis 181:107689, <doi:10.1016/j.csda.2022.107689>.

This package implements reversal association pattern analysis for categorical data. Detects sub-tables exhibiting reversal associations in contingency tables, provides visualization tools, and supports simulation-based validation for complex I Ã J tables.

This package provides a fast calculation of the Blyth-Still-Casella confidence interval. The implementation follows the StatXact 9 manual (Cytel 2010) and "Refining Binomial Confidence Intervals" by George Casella (1986) <doi:10.2307/3314658>.

Statistical tools for the Mallows-Binomial model, the first joint statistical model for preference learning for rankings and ratings. This project was supported by the National Science Foundation under Grant No. 2019901.

This package provides a general-purpose optimisation engine that supports i) Monte Carlo optimisation with Metropolis criterion [Metropolis et al. (1953) <doi:10.1063/1.1699114>, Hastings (1970) <doi:10.1093/biomet/57.1.97>] and Acceptance Ratio Simulated Annealing [Kirkpatrick et al. (1983) <doi:10.1126/science.220.4598.671>, Ä erný (1985) <doi:10.1007/BF00940812>] on multiple cores, and ii) Acceptance Ratio Replica Exchange Monte Carlo Optimisation. In each case, the system pseudo-temperature is dynamically adjusted such that the observed acceptance ratio is kept near to the desired (fixed or changing) acceptance ratio.

Point and interval estimation of linear parameters with data obtained from complex surveys (including stratified and clustered samples) when randomization techniques are used. The randomized response technique was developed to obtain estimates that are more valid when studying sensitive topics. Estimators and variances for 14 randomized response methods for qualitative variables and 7 randomized response methods for quantitative variables are also implemented. In addition, some data sets from surveys with these randomization methods are included in the package.

Standard and extensible Eddy-Covariance data post-processing (Wutzler et al. (2018) <doi:10.5194/bg-15-5015-2018>) includes uStar-filtering, gap-filling, and flux-partitioning. The Eddy-Covariance (EC) micrometeorological technique quantifies continuous exchange fluxes of gases, energy, and momentum between an ecosystem and the atmosphere. It is important for understanding ecosystem dynamics and upscaling exchange fluxes. (Aubinet et al. (2012) <doi:10.1007/978-94-007-2351-1>). This package inputs pre-processed (half-)hourly data and supports further processing. First, a quality-check and filtering is performed based on the relationship between measured flux and friction velocity (uStar) to discard biased data (Papale et al. (2006) <doi:10.5194/bg-3-571-2006>). Second, gaps in the data are filled based on information from environmental conditions (Reichstein et al. (2005) <doi:10.1111/j.1365-2486.2005.001002.x>). Third, the net flux of carbon dioxide is partitioned into its gross fluxes in and out of the ecosystem by night-time based and day-time based approaches (Lasslop et al. (2010) <doi:10.1111/j.1365-2486.2009.02041.x>).

Standardized methods for calculating common important derived physical features of lakes including water density based based on temperature, thermal layers, thermocline depth, lake number, Wedderburn number, Schmidt stability and others.

Simulation of phenotype / genotype data under assortative mating. Includes functions for generating Bahadur order-2 multivariate Bernoulli variables with general and diagonal-plus-low-rank correlation structures. Further details are provided in: Border and Malik (2022) <doi:10.1101/2022.10.13.512132>.

This package provides bioaccumulation factors from a toxicokinetic model fitted to accumulation-depuration data. It is designed to fulfil the requirements of regulators when examining applications for market authorization of active substances.

This package provides a collection of methods for estimating the basic reproduction number (R0) of infectious diseases. Features a web application to interface with the estimators. Uses the models from: Fisman et al. (2013) <DOI:10.1371/journal.pone.0083622>, Bettencourt and Ribeiro (2008) <DOI:10.1371/journal.pone.0002185>, and White and Pagano (2008) <DOI:10.1002/sim.3136>. Includes datasets for Canadian national and provincial COVID-19 case counts provided by Berry et al. (2021) <DOI:10.1038/s41597-021-00955-2>.

This package implements the algorithm by Pourahmadi and Wang (2015) <doi:10.1016/j.spl.2015.06.015> for generating a random p x p correlation matrix. Briefly, the idea is to represent the correlation matrix using Cholesky factorization and p(p-1)/2 hyperspherical coordinates (i.e., angles), sample the angles from a particular distribution and then convert to the standard correlation matrix form. The angles are sampled from a distribution with pdf proportional to sin^k(theta) (0 < theta < pi, k >= 1) using the efficient sampling algorithm described in Enes Makalic and Daniel F. Schmidt (2018) <arXiv:1809.05212>.

This package provides functions for assessing variable relations and associations prior to modeling with a Random Forest algorithm (although these are relevant for any predictive model). Metrics such as partial correlations and variance inflation factors are tabulated as well as plotted for the user. A function is available for tuning the main Random Forest hyper-parameter based on model performance and variable importance metrics. This grid-search technique provides tables and plots showing the effect of the main hyper-parameter on each of the assessment metrics. It also returns each of the evaluated models to the user. The package also provides superior variable importance plots for individual models. All of the plots are developed so that the user has the ability to edit and improve further upon the plots. Derivations and methodology are described in Bladen (2022) <https://digitalcommons.usu.edu/etd/8587/>.

This package provides a collection of programs for plotting SKEW-T,log p diagrams and wind profiles for data collected by radiosondes (the typical weather balloon-borne instrument). The format of this plot with companion lines to assess atmospheric stability are both standard in meteorology and difficult to create from basic graphics functions. Hence this package. One novel feature is being able add several profiles to the same plot for comparison. Use "help(ExampleSonde)" for an explanation of the variables needed and how they should be named in a data frame. See <https://github.com/dnychka/Radiosonde> for the package home page.

Quantifies submission risk using a Failure Modes and Effects Analysis (FMEA)-inspired framework (probability, impact, detectability). Builds risk registers from evidence, computes Risk Priority Numbers (RPN), classifies risk levels, and emits standardized R4SUB (R for Regulatory Submission) evidence table rows via r4subcore'. Supports risk mitigation tracking and trend analysis across submission milestones.

The key function get_vintage_data() returns a dataframe and is the window into the Census Bureau API requiring just a dataset name, vintage(year), and vector of variable names for survey estimates/percentages. Other functions assist in searching for available datasets, geographies, group/variable concepts of interest. Also provided are functions to access and layer (via standard piping) displayable geometries for the US, states, counties, blocks/tracts, roads, landmarks, places, and bodies of water. Joining survey data with many of the geometry functions is built-in to produce choropleth maps.

Statistical estimation of revealed preference models from data collected on bipartite matchings. The models are for matchings within a bipartite population where individuals have utility for people based on known and unknown characteristics. People can form a partnership or remain unpartnered. The model represents both the availability of potential partners of different types and preferences of individuals for such people. The software estimates preference parameters based on sample survey data on partnerships and population composition. The simulation of matchings and goodness-of-fit are considered. See Goyal, Handcock, Jackson, Rendall and Yeung (2022) <doi:10.1093/jrsssa/qnad031>.

The Stochastic Dominance (SD) is the classical way of comparing two random prospects, using their distribution functions. Almost Stochastic Dominance (ASD) has also been developed to cover the SD failures due to the extreme utility functions. This package focuses on classical and heuristic methods for testing the first and second SD and ASD methods given the probability mass function (PMF) of the random prospects. The goal is to apply these methods easily, efficiently, and effectively on real-world datasets. For more details see Hanoch and Levy (1969) <doi:10.2307/2296431>, Leshno and Levy (2002) <doi:10.1287/mnsc.48.8.1074.169>, and Tzeng et al. (2012) <doi:10.1287/mnsc.1120.1616>.