This package implements code to identify lexical competitors in a given list of words. We include many of the standard competitor types used in spoken word recognition research, such as functions to find cohorts, neighbors, and rhymes, amongst many others. The package includes documentation for using a variety of lexicon files, including those with form codes made up of multiple letters (i.e., phoneme codes) and also basic orthographies. Importantly, the code makes use of multiple CPU cores and vectorization when possible, making it extremely fast and able to handle large lexicons. Additionally, the package contains documentation for users to easily write new functions, allowing researchers to examine other relationships within a lexicon. Preprint: <https://osf.io/preprints/psyarxiv/8dyru/>. Open access: <doi:10.3758/s13428-021-01667-6>. Citation: Li, Z., Crinnion, A.M. & Magnuson, J.S. (2021). <doi:10.3758/s13428-021-01667-6>.

An implementation of DuMouchel's (1999) <doi:10.1080/00031305.1999.10474456> Bayesian data mining method for the market basket problem. Calculates Empirical Bayes Geometric Mean (EBGM) and posterior quantile scores using the Gamma-Poisson Shrinker (GPS) model to find unusually large cell counts in large, sparse contingency tables. Can be used to find unusually high reporting rates of adverse events associated with products. In general, can be used to mine any database where the co-occurrence of two variables or items is of interest. Also calculates relative and proportional reporting ratios. Builds on the work of the PhViD package, from which much of the code is derived. Some of the added features include stratification to adjust for confounding variables and data squashing to improve computational efficiency. Includes an implementation of the EM algorithm for hyperparameter estimation loosely derived from the mederrRank package.

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>.

Urban water and sanitation survey dataset collected by Water and Sanitation for the Urban Poor (WSUP) with technical support from Valid International. These citywide surveys have been collecting data allowing water and sanitation service levels across the entire city to be characterised, while also allowing more detailed data to be collected in areas of the city of particular interest. These surveys are intended to generate useful information for others working in the water and sanitation sector. Current release version includes datasets collected from a survey conducted in Dhaka, Bangladesh in March 2017. This survey in Dhaka is one of a series of surveys to be conducted by WSUP in various cities in which they operate including Accra, Ghana; Nakuru, Kenya; Antananarivo, Madagascar; Maputo, Mozambique; and, Lusaka, Zambia. This package will be updated once the surveys in other cities are completed and datasets have been made available.

The DaMiRseq package offers a tidy pipeline of data mining procedures to identify transcriptional biomarkers and exploit them for both binary and multi-class classification purposes. The package accepts any kind of data presented as a table of raw counts and allows including both continous and factorial variables that occur with the experimental setting. A series of functions enable the user to clean up the data by filtering genomic features and samples, to adjust data by identifying and removing the unwanted source of variation (i.e. batches and confounding factors) and to select the best predictors for modeling. Finally, a "stacking" ensemble learning technique is applied to build a robust classification model. Every step includes a checkpoint that the user may exploit to assess the effects of data management by looking at diagnostic plots, such as clustering and heatmaps, RLE boxplots, MDS or correlation plot.

Extensive functions for bivariate copula (bicopula) computations and related operations for bicopula theory. The lower, upper, product, and select other bicopula are implemented along with operations including the diagonal, survival copula, dual of a copula, co-copula, and numerical bicopula density. Level sets, horizontal and vertical sections are supported. Numerical derivatives and inverses of a bicopula are provided through which simulation is implemented. Bicopula composition, convex combination, asymmetry extension, and products also are provided. Support extends to the Kendall Function as well as the Lmoments thereof. Kendall Tau, Spearman Rho and Footrule, Gini Gamma, Blomqvist Beta, Hoeffding Phi, Schweizer- Wolff Sigma, tail dependency, tail order, skewness, and bivariate Lmoments are implemented, and positive/negative quadrant dependency, left (right) increasing (decreasing) are available. Other features include Kullback-Leibler Divergence, Vuong Procedure, spectral measure, and Lcomoments for inference, maximum likelihood, and AIC, BIC, and RMSE for goodness-of-fit.

The experiment selector cross-validated targeted maximum likelihood estimator (ES-CVTMLE) aims to select the experiment that optimizes the bias-variance tradeoff for estimating a causal average treatment effect (ATE) where different experiments may include a randomized controlled trial (RCT) alone or an RCT combined with real-world data. Using cross-validation, the ES-CVTMLE separates the selection of the optimal experiment from the estimation of the ATE for the chosen experiment. The estimated bias term in the selector is a function of the difference in conditional mean outcome under control for the RCT compared to the combined experiment. In order to help include truly unbiased external data in the analysis, the estimated average treatment effect on a negative control outcome may be added to the bias term in the selector. For more details about this method, please see Dang et al. (2022) <arXiv:2210.05802>.

An implementation of ADPclust clustering procedures (Fast Clustering Using Adaptive Density Peak Detection). The work is built and improved upon the idea of Rodriguez and Laio (2014)<DOI:10.1126/science.1242072>. ADPclust clusters data by finding density peaks in a density-distance plot generated from local multivariate Gaussian density estimation. It includes an automatic centroids selection and parameter optimization algorithm, which finds the number of clusters and cluster centroids by comparing average silhouettes on a grid of testing clustering results; It also includes a user interactive algorithm that allows the user to manually selects cluster centroids from a two dimensional "density-distance plot". Here is the research article associated with this package: "Wang, Xiao-Feng, and Yifan Xu (2015)<DOI:10.1177/0962280215609948> Fast clustering using adaptive density peak detection." Statistical methods in medical research". url: http://smm.sagepub.com/content/early/2015/10/15/0962280215609948.abstract.

This package provides basic functionalities to calculate the position of satellites given a known state vector. The package includes implementations of the SGP4 and SDP4 simplified perturbation models to propagate orbital state vectors, as well as utilities to read TLE files and convert coordinates between different frames of reference. Several of the functionalities of the package (including the high-precision numerical orbit propagator) require the coefficients and data included in the asteRiskData package, available in a drat repository. To install this data package, run install.packages("asteRiskData", repos="https://rafael-ayala.github.io/drat/")'. Felix R. Hoots, Ronald L. Roehrich and T.S. Kelso (1988) <https://celestrak.org/NORAD/documentation/spacetrk.pdf>. David Vallado, Paul Crawford, Richard Hujsak and T.S. Kelso (2012) <doi:10.2514/6.2006-6753>. Felix R. Hoots, Paul W. Schumacher Jr. and Robert A. Glover (2014) <doi:10.2514/1.9161>.

This package provides functions to compute fuzzy versions of species occurrence patterns based on presence-absence data (including inverse distance interpolation, trend surface analysis, and prevalence-independent favourability obtained from probability of presence), as well as pair-wise fuzzy similarity (based on fuzzy logic versions of commonly used similarity indices) among those occurrence patterns. Includes also functions for model consensus and comparison (overlap and fuzzy similarity, fuzzy loss, fuzzy gain), and for data preparation, such as obtaining unique abbreviations of species names, defining the background region, cleaning and gridding (thinning) point occurrence data onto raster maps, selecting among (pseudo)absences to address survey bias, converting species lists (long format) to presence-absence tables (wide format), transposing part of a data frame, selecting relevant variables for models, assessing the false discovery rate, or analysing and dealing with multicollinearity. Initially described in Barbosa (2015) <doi:10.1111/2041-210X.12372>.

This package provides functions to calculate seed germination and seedling emergence and growth indexes. The main indexes for germination and seedling emergence, considering the time for seed germinate are: T10, T50 and T90, in Farooq et al. (2005) <10.1111/j.1744-7909.2005.00031.x>; and MGT, in Labouriau (1983). Considering the germination speed are: Germination Speed Index, in Maguire (1962), Mean Germination Rate, in Labouriau (1983); considering the homogeneity of germination are: Coefficient of Variation of the Germination Time, in Carvalho et al. (2005) <10.1590/S0100-84042005000300018>, and Variance of Germination, in Labouriau (1983); Uncertainty, in Labouriau and Valadares (1976) <ISSN:0001-3765>; and Synchrony, in Primack (1980). The main seedling indexes are Growth, in Sako (2001), Uniformity, in Sako (2001) and Castan et al. (2018) <doi:10.1590/1678-992x-2016-0401>; and Vigour, in Medeiros and Pereira (2018) <doi:10.1590/1983-40632018v4852340>.

General linear modeling with multiple responses (MANCOVA). An overall p-value for each model term is calculated by the 50-50 MANOVA method by Langsrud (2002) <doi:10.1111/1467-9884.00320>, which handles collinear responses. Rotation testing, described by Langsrud (2005) <doi:10.1007/s11222-005-4789-5>, is used to compute adjusted single response p-values according to familywise error rates and false discovery rates (FDR). The approach to FDR is described in the appendix of Moen et al. (2005) <doi:10.1128/AEM.71.4.2086-2094.2005>. Unbalanced designs are handled by Type II sums of squares as argued in Langsrud (2003) <doi:10.1023/A:1023260610025>. Furthermore, the Type II philosophy is extended to continuous design variables as described in Langsrud et al. (2007) <doi:10.1080/02664760701594246>. This means that the method is invariant to scale changes and that common pitfalls are avoided.

Datasets and functions for the book "Modélisation statistique par la pratique avec R", F. Bertrand, E. Claeys and M. Maumy-Bertrand (2019, ISBN:9782100793525, Dunod, Paris). The first chapter of the book is dedicated to an introduction to the R statistical software. The second chapter deals with correlation analysis: Pearson, Spearman and Kendall simple, multiple and partial correlation coefficients. New wrapper functions for permutation tests or bootstrap of matrices of correlation are provided with the package. The third chapter is dedicated to data exploration with factorial analyses (PCA, CA, MCA, MDA) and clustering. The fourth chapter is dedicated to regression analysis: fitting and model diagnostics are detailed. The exercises focus on covariance analysis, logistic regression, Poisson regression, two-way analysis of variance for fixed or random factors. Various example datasets are shipped with the package: for instance on pokemon, world of warcraft, house tasks or food nutrition analyses.

Multilevel models (mixed effects models) are the statistical tool of choice for analyzing multilevel data (Searle et al, 2009). These models account for the correlated nature of observations within higher level units by adding group-level error terms that augment the singular residual error of a standard OLS regression. Multilevel and mixed effects models often require specialized data pre-processing and further post-estimation derivations and graphics to gain insight into model results. The package presented here, mlmtools', is a suite of pre- and post-estimation tools for multilevel models in R'. Package implements post-estimation tools designed to work with models estimated using lme4''s (Bates et al., 2014) lmer() function, which fits linear mixed effects regression models. Searle, S. R., Casella, G., & McCulloch, C. E. (2009, ISBN:978-0470009598). Bates, D., Mächler, M., Bolker, B., & Walker, S. (2014) <doi:10.18637/jss.v067.i01>.

The methods discussed in this package are new non-parametric methods based on sequential normal scores SNS (Conover et al (2017) <doi:10.1080/07474946.2017.1360091>), designed for sequences of observations, usually time series data, which may occur singly or in batches, and may be univariate or multivariate. These methods are designed to detect changes in the process, which may occur as changes in location (mean or median), changes in scale (standard deviation, or variance), or other changes of interest in the distribution of the observations, over the time observed. They usually apply to large data sets, so computations need to be simple enough to be done in a reasonable time on a computer, and easily updated as each new observation (or batch of observations) becomes available. Some examples and more detail in SNS is presented in the work by Conover et al (2019) <arXiv:1901.04443>.

Screen for and analyze non-linear sparse direct effects in the presence of unobserved confounding using the spectral deconfounding techniques (Ä evid, Bühlmann, and Meinshausen (2020)<jmlr.org/papers/v21/19-545.html>, Guo, Ä evid, and Bühlmann (2022) <doi:10.1214/21-AOS2152>). These methods have been shown to be a good estimate for the true direct effect if we observe many covariates, e.g., high-dimensional settings, and we have fairly dense confounding. Even if the assumptions are violated, it seems like there is not much to lose, and the deconfounded models will, in general, estimate a function closer to the true one than classical least squares optimization. SDModels provides functions SDAM() for Spectrally Deconfounded Additive Models (Scheidegger, Guo, and Bühlmann (2025) <doi:10.1145/3711116>) and SDForest() for Spectrally Deconfounded Random Forests (Ulmer, Scheidegger, and Bühlmann (2025) <doi:10.48550/arXiv.2502.03969>).

We developed a lightweight machine learning tool for RNA profiling of acute lymphoblastic leukemia (ALL), however, it can be used for any problem where multiple classes need to be identified from multi-dimensional data. The methodology is described in Makinen V-P, Rehn J, Breen J, Yeung D, White DL (2022) Multi-cohort transcriptomic subtyping of B-cell acute lymphoblastic leukemia, International Journal of Molecular Sciences 23:4574, <doi:10.3390/ijms23094574>. The classifier contains optimized mean profiles of the classes (centroids) as observed in the training data, and new samples are matched to these centroids using the shortest Euclidean distance. Centroids derived from a dataset of 1,598 ALL patients are included, but users can train the models with their own data as well. The output includes both numerical and visual presentations of the classification results. Samples with mixed features from multiple classes or atypical values are also identified.

This package provides advanced statistical methods to describe and predict customers purchase behavior in a non-contractual setting. It uses historic transaction records to fit a probabilistic model, which then allows to compute quantities of managerial interest on a cohort- as well as on a customer level (Customer Lifetime Value, Customer Equity, P(alive), etc.). This package complements the BTYD package by providing several additional buy-till-you-die models, that have been published in the marketing literature, but whose implementation are complex and non-trivial. These models are: NBD [Ehrenberg (1959) <doi:10.2307/2985810>], MBG/NBD [Batislam et al (2007) <doi:10.1016/j.ijresmar.2006.12.005>], (M)BG/CNBD-k [Reutterer et al (2020) <doi:10.1016/j.ijresmar.2020.09.002>], Pareto/NBD (HB) [Abe (2009) <doi:10.1287/mksc.1090.0502>] and Pareto/GGG [Platzer and Reutterer (2016) <doi:10.1287/mksc.2015.0963>].

Offers a set of tools for visualizing and analyzing size and power properties of the test for equal predictive accuracy, the Diebold-Mariano test that is based on heteroskedasticity and autocorrelation-robust (HAR) inference. A typical HAR inference is involved with non-parametric estimation of the long-run variance, and one of its tuning parameters, the truncation parameter, trades off a size and power. Lazarus, Lewis, and Stock (2021)<doi:10.3982/ECTA15404> theoretically characterize the size-power frontier for the Gaussian multivariate location model. ForeComp computes and visualizes the finite-sample size-power frontier of the Diebold-Mariano test based on fixed-b asymptotics together with the Bartlett kernel. To compute the finite-sample size and power, it works with the best approximating ARMA process to the given dataset. It informs the user how their choice of the truncation parameter performs and how robust the testing outcomes are.

An increasingly important source of health-related bibliographic content are preprints - preliminary versions of research articles that have yet to undergo peer review. The two preprint repositories most relevant to health-related sciences are medRxiv <https://www.medrxiv.org/> and bioRxiv <https://www.biorxiv.org/>, both of which are operated by the Cold Spring Harbor Laboratory. medrxivr provides programmatic access to the Cold Spring Harbour Laboratory (CSHL) API <https://api.biorxiv.org/>, allowing users to easily download medRxiv and bioRxiv preprint metadata (e.g. title, abstract, publication date, author list, etc) into R. medrxivr also provides functions to search the downloaded preprint records using regular expressions and Boolean logic, as well as helper functions that allow users to export their search results to a .BIB file for easy import to a reference manager and to download the full-text PDFs of preprints matching their search criteria.

This package provides functions for computing test subscores using different methods in both classical test theory (CTT) and item response theory (IRT). This package enables three types of subscoring methods within the framework of CTT and IRT, including (1) Wainer's augmentation method (Wainer et. al., 2001) <doi:10.4324/9781410604729>, (2) Haberman's subscoring methods (Haberman, 2008) <doi:10.3102/1076998607302636>, and (3) Yen's objective performance index (OPI; Yen, 1987) <https://www.ets.org/research/policy_research_reports/publications/paper/1987/hrap>. It also includes functions to compute Proportional Reduction of Mean Squared Errors (PRMSEs) in Haberman's methods which are used to examine whether test subscores are of added value. In addition, the package includes a function to assess the local independence assumption of IRT with Yen's Q3 statistic (Yen, 1984 <doi:10.1177/014662168400800201>; Yen, 1993 <doi:10.1111/j.1745-3984.1993.tb00423.x>).

In the observational study design stage, matching/weighting methods are conducted. However, when many background variables are present, the decision as to which variables to prioritize for matching/weighting is not trivial. Thus, the joint treatment-outcome variable importance plots are created to guide variable selection. The joint variable importance plots enhance variable comparisons via unadjusted bias curves derived under the omitted variable bias framework. The plots translate variable importance into recommended values for tuning parameters in existing methods. Post-matching and/or weighting plots can also be used to visualize and assess the quality of the observational study design. The method motivation and derivation is presented in "Prioritizing Variables for Observational Study Design using the Joint Variable Importance Plot" by Liao et al. (2024) <doi:10.1080/00031305.2024.2303419>. See the package paper by Liao and Pimentel (2024) <doi:10.21105/joss.06093> for a beginner friendly user introduction.

This package contains functions for multiple imputation which complements existing functionality in R. In particular, several imputation methods for the mice package (van Buuren & Groothuis-Oudshoorn, 2011, <doi:10.18637/jss.v045.i03>) are implemented. Main features of the miceadds package include plausible value imputation (Mislevy, 1991, <doi:10.1007/BF02294457>), multilevel imputation for variables at any level or with any number of hierarchical and non-hierarchical levels (Grund, Luedtke & Robitzsch, 2018, <doi:10.1177/1094428117703686>; van Buuren, 2018, Ch.7, <doi:10.1201/9780429492259>), imputation using partial least squares (PLS) for high dimensional predictors (Robitzsch, Pham & Yanagida, 2016), nested multiple imputation (Rubin, 2003, <doi:10.1111/1467-9574.00217>), substantive model compatible imputation (Bartlett et al., 2015, <doi:10.1177/0962280214521348>), and features for the generation of synthetic datasets (Reiter, 2005, <doi:10.1111/j.1467-985X.2004.00343.x>; Nowok, Raab, & Dibben, 2016, <doi:10.18637/jss.v074.i11>).

User-friendly analysis of hierarchical multinomial processing tree (MPT) models that are often used in cognitive psychology. Implements the latent-trait MPT approach (Klauer, 2010) <DOI:10.1007/s11336-009-9141-0> and the beta-MPT approach (Smith & Batchelder, 2010) <DOI:10.1016/j.jmp.2009.06.007> to model heterogeneity of participants. MPT models are conveniently specified by an .eqn-file as used by other MPT software and data are provided by a .csv-file or directly in R. Models are either fitted by calling JAGS or by an MPT-tailored Gibbs sampler in C++ (only for nonhierarchical and beta MPT models). Provides tests of heterogeneity and MPT-tailored summaries and plotting functions. A detailed documentation is available in Heck, Arnold, & Arnold (2018) <DOI:10.3758/s13428-017-0869-7> and a tutorial on MPT modeling can be found in Schmidt, Erdfelder, & Heck (2022) <DOI:10.31234/osf.io/gh8md>.