This package provides a set of functions to perform distribution-free Bayesian analyses. Included are Bayesian analogues to the frequentist Mann-Whitney U test, the Wilcoxon Signed-Ranks test, Kendall's Tau Rank Correlation Coefficient, Goodman and Kruskal's Gamma, McNemar's Test, the binomial test, the sign test, the median test, as well as distribution-free methods for testing contrasts among condition and for computing Bayes factors for hypotheses. The package also includes procedures to estimate the power of distribution-free Bayesian tests based on data simulations using various probability models for the data. The set of functions provide data analysts with a set of Bayesian procedures that avoids requiring parametric assumptions about measurement error and is robust to problem of extreme outlier scores.

This package provides a comprehensive framework for visualizing associations and interaction structures in matrix-formatted data using Generalized Association Plots (GAP). The package implements multiple proximity computation methods (e.g., correlation, distance metrics), ordering techniques including hierarchical clustering (HCT) and Rank-2-Ellipse (R2E) seriation, and optional flipping strategies to enhance visual symmetry. It supports a variety of covariate-based color annotations, allows flexible customization of layout and output, and is suitable for analyzing multivariate data across domains such as social sciences, genomics, and medical research. The method is based on Generalized Association Plots introduced by Chen (2002) <https://www3.stat.sinica.edu.tw/statistica/J12N1/J12N11/J12N11.html> and further extended by Wu, Tien, and Chen (2010) <doi:10.1016/j.csda.2008.09.029>.

Nested loop cross validation for classification purposes for misclassification error rate estimation. The package supports several methodologies for feature selection: random forest, Student t-test, limma, and provides an interface to the following classification methods in the MLInterfaces package: linear, quadratic discriminant analyses, random forest, bagging, prediction analysis for microarray, generalized linear model, support vector machine (svm and ksvm). Visualizations to assess the quality of the classifier are included: plot of the ranks of the features, scores plot for a specific classification algorithm and number of features, misclassification rate for the different number of features and classification algorithms tested and ROC plot. For further details about the methodology, please check: Markus Ruschhaupt, Wolfgang Huber, Annemarie Poustka, and Ulrich Mansmann (2004) <doi:10.2202/1544-6115.1078>.

Analysis and visualization of similarities between epilepsy ontologies based on text mining results by comparing ranked lists of co-occurring drug terms in the BioASQ corpus. The ranked result lists of neurological drug terms co-occurring with terms from the epilepsy ontologies EpSO, ESSO, EPILONT, EPISEM and FENICS undergo further analysis. The source data to create the ranked lists of drug names is produced using the text mining workflows described in Mueller, Bernd and Hagelstein, Alexandra (2016) <doi:10.4126/FRL01-006408558>, Mueller, Bernd et al. (2017) <doi:10.1007/978-3-319-58694-6_22>, Mueller, Bernd and Rebholz-Schuhmann, Dietrich (2020) <doi:10.1007/978-3-030-43887-6_52>, and Mueller, Bernd et al. (2022) <doi:10.1186/s13326-021-00258-w>.

This package provides a collection of functions to perform core tasks within Energy Trading and Risk Management (ETRM). Calculation of maximum smoothness forward price curves for electricity and natural gas contracts with flow delivery, as presented in F. E. Benth, S. Koekebakker, and F. Ollmar (2007) <doi:10.3905/jod.2007.694791> and F. E. Benth, J. S. Benth, and S. Koekebakker (2008) <doi:10.1142/6811>. Portfolio insurance trading strategies for price risk management in the forward market, see F. Black (1976) <doi:10.1016/0304-405X(76)90024-6>, T. Bjork (2009) <https://EconPapers.repec.org/RePEc:oxp:obooks:9780199574742>, F. Black and R. W. Jones (1987) <doi:10.3905/jpm.1987.409131> and H. E. Leland (1980) <http://www.jstor.org/stable/2327419>.

This package provides a set of objects and functions for Bayes Linear emulation and history matching. Core functionality includes automated training of emulators to data, diagnostic functions to ensure suitability, and a variety of proposal methods for generating waves of points. For details on the mathematical background, there are many papers available on the topic (see references attached to function help files or the below references); for details of the functions in this package, consult the manual or help files. Iskauskas, A, et al. (2024) <doi:10.18637/jss.v109.i10>. Bower, R.G., Goldstein, M., and Vernon, I. (2010) <doi:10.1214/10-BA524>. Craig, P.S., Goldstein, M., Seheult, A.H., and Smith, J.A. (1997) <doi:10.1007/978-1-4612-2290-3_2>.

Extends parametric empirical Bayes (PEB) for longitudinal biomarker screening with a time-gap-aware standardization layer, covariate adjustment, and objective-driven multi-marker weighting. The layer models each subject's biomarker history with a random intercept (and an optional random slope) and autocorrelated, gap-scaled residuals, so that prediction uncertainty grows with the time between visits and per-visit specificity is preserved under irregular sampling. Marker weights are learned to optimize a user-selected clinical objective -- maximizing sensitivity at a fixed specificity, extending detection lead time, or a combined objective -- with optional feature selection and a choice of scalar or multivariate combiner. Functions for fitting, prediction, and evaluation (sensitivity, lead time, and specificity at chosen operating points) are provided. A manuscript describing the method is in preparation.

Quasi likelihood-based methods for estimating linear and log-linear Poisson Network Autoregression models with p lags and covariates. Tools for testing the linearity versus several non-linear alternatives. Tools for simulation of multivariate count distributions, from linear and non-linear PNAR models, by using a specific copula construction. References include: Armillotta, M. and K. Fokianos (2023). "Nonlinear network autoregression". Annals of Statistics, 51(6): 2526--2552. <doi:10.1214/23-AOS2345>. Armillotta, M. and K. Fokianos (2024). "Count network autoregression". Journal of Time Series Analysis, 45(4): 584--612. <doi:10.1111/jtsa.12728>. Armillotta, M., Tsagris, M. and Fokianos, K. (2023). "Inference for Network Count Time Series with the R Package PNAR". The R Journal, 15/4: 255--269. <doi:10.32614/RJ-2023-094>.

Utilizes the Reliability-Adjusted Product Indicator (RAPI) method to estimate effects among latent variables, thus allowing for more precise definition and analysis of mediation and moderation models. Our simulation studies reveal that while silp may exhibit instability with smaller sample sizes and lower reliability scores (e.g., N = 100, omega = 0.7), implementing nearest positive definite matrix correction and bootstrap confidence interval estimation can significantly ameliorate this volatility. When these adjustments are applied, silp achieves estimations akin in quality to those derived from LMS. In conclusion, the silp package is a valuable tool for researchers seeking to explore complex relational structures between variables without resorting to commercial software. Cheung et al.(2021)<doi:10.1007/s10869-020-09717-0> Hsiao et al.(2018)<doi:10.1177/0013164416679877>.

Fit Bayesian generalized (non-)linear multivariate multilevel models using Stan for full Bayesian inference. A wide range of distributions and link functions are supported, allowing users to fit -- among others -- linear, robust linear, count data, survival, response times, ordinal, zero-inflated, hurdle, and even self-defined mixture models all in a multilevel context. Further modeling options include non-linear and smooth terms, auto-correlation structures, censored data, meta-analytic standard errors, and quite a few more. In addition, all parameters of the response distribution can be predicted in order to perform distributional regression. Prior specifications are flexible and explicitly encourage users to apply prior distributions that actually reflect their beliefs. Model fit can easily be assessed and compared with posterior predictive checks and leave-one-out cross-validation.

Most analyses of Affymetrix GeneChip data (including tranditional 3 arrays and exon arrays and Human Transcriptome Array 2.0) are based on point estimates of expression levels and ignore the uncertainty of such estimates. By propagating uncertainty to downstream analyses we can improve results from microarray analyses. For the first time, the puma package makes a suite of uncertainty propagation methods available to a general audience. In additon to calculte gene expression from Affymetrix 3 arrays, puma also provides methods to process exon arrays and produces gene and isoform expression for alternative splicing study. puma also offers improvements in terms of scope and speed of execution over previously available uncertainty propagation methods. Included are summarisation, differential expression detection, clustering and PCA methods, together with useful plotting functions.

Estimate a total causal effect from observational data under linearity and causal sufficiency. The observational data is supposed to be generated from a linear structural equation model (SEM) with independent and additive noise. The underlying causal DAG associated the SEM is required to be known up to a maximally oriented partially directed graph (MPDAG), which is a general class of graphs consisting of both directed and undirected edges, including CPDAGs (i.e., essential graphs) and DAGs. Such graphs are usually obtained with structure learning algorithms with added background knowledge. The program is able to estimate every identified effect, including single and multiple treatment variables. Moreover, the resulting estimate has the minimal asymptotic covariance (and hence shortest confidence intervals) among all estimators that are based on the sample covariance.

This package implements shape-based clustering algorithms for multidimensional longitudinal data based on the Fréchet distance. It implements two main methods: MFKmL (Multidimensional Fréchet distance-based K-means for Longitudinal data), an extension of the K-means algorithm using the Fréchet distance originally developed in the kmlShape package, adapted for multidimensional trajectories; and SFKmL (Sparse multidimensional Fréchet distance-based K-medoids for Longitudinal data), a K-medoids-based clustering algorithm that incorporates variable selection. These tools are designed to enhance clustering performance in high-dimensional longitudinal data settings, particularly those with time delays, variations in trajectory speed, irregular sampling intervals, and noise. This package implements methods derived from Kang et al. (2023) <doi:10.1007/s11222-023-10237-z>.

Allows to estimate dynamic model averaging, dynamic model selection and median probability model. The original methods are implemented, as well as, selected further modifications of these methods. In particular the user might choose between recursive moment estimation and exponentially moving average for variance updating. Inclusion probabilities might be modified in a way using Google Trends'. The code is written in a way which minimises the computational burden (which is quite an obstacle for dynamic model averaging if many variables are used). For example, this package allows for parallel computations and Occam's window approach. The package is designed in a way that is hoped to be especially useful in economics and finance. Main reference: Raftery, A.E., Karny, M., Ettler, P. (2010) <doi:10.1198/TECH.2009.08104>.

This package implements methods and functions to calibrate time-specific niche models (multi-temporal calibration), letting users execute a strict calibration and selection process of niche models based on ellipsoids, as well as functions to project the potential distribution in the present and in global change scenarios.The tenm package has functions to recover information that may be lost or overlooked while applying a data curation protocol. This curation involves preserving occurrences that may appear spatially redundant (occurring in the same pixel) but originate from different time periods. A novel aspect of this package is that it might reconstruct the fundamental niche more accurately than mono-calibrated approaches. The theoretical background of the package can be found in Peterson et al. (2011)<doi:10.5860/CHOICE.49-6266>.

Single-cell RNA-sequencing (scRNA-seq) has made it possible to profile gene expression in tissues at high resolution. An important preprocessing step prior to performing downstream analyses is to identify and remove cells with poor or degraded sample quality using quality control (QC) metrics. Two widely used QC metrics to identify a ‘low-quality’ cell are (i) if the cell includes a high proportion of reads that map to mitochondrial DNA encoded genes (mtDNA) and (ii) if a small number of genes are detected. miQC is data-driven QC metric that jointly models both the proportion of reads mapping to mtDNA and the number of detected genes with mixture models in a probabilistic framework to predict the low-quality cells in a given dataset.

Discriminant Non-Negative Matrix Factorization aims to extend the Non-negative Matrix Factorization algorithm in order to extract features that enforce not only the spatial locality, but also the separability between classes in a discriminant manner. It refers to three article, Zafeiriou, Stefanos, et al. "Exploiting discriminant information in nonnegative matrix factorization with application to frontal face verification." Neural Networks, IEEE Transactions on 17.3 (2006): 683-695. Kim, Bo-Kyeong, and Soo-Young Lee. "Spectral Feature Extraction Using dNMF for Emotion Recognition in Vowel Sounds." Neural Information Processing. Springer Berlin Heidelberg, 2013. and Lee, Soo-Young, Hyun-Ah Song, and Shun-ichi Amari. "A new discriminant NMF algorithm and its application to the extraction of subtle emotional differences in speech." Cognitive neurodynamics 6.6 (2012): 525-535.

Interactions between different biological entities are crucial for the function of biological systems. In such networks, nodes represent biological elements, such as genes, proteins and microbes, and their interactions can be defined by edges, which can be either binary or weighted. The dysregulation of these networks can be associated with different clinical conditions such as diseases and response to treatments. However, such variations often occur locally and do not concern the whole network. To capture local variations of such networks, we propose multiplex network differential analysis (MNDA). MNDA allows to quantify the variations in the local neighborhood of each node (e.g. gene) between the two given clinical states, and to test for statistical significance of such variation. Yousefi et al. (2023) <doi:10.1101/2023.01.22.525058>.

Bayesian Additive Regression Kernels (BARK) provides an implementation for non-parametric function estimation using Levy Random Field priors for functions that may be represented as a sum of additive multivariate kernels. Kernels are located at every data point as in Support Vector Machines, however, coefficients may be heavily shrunk to zero under the Cauchy process prior, or even, set to zero. The number of active features is controlled by priors on precision parameters within the kernels, permitting feature selection. For more details see Ouyang, Z (2008) "Bayesian Additive Regression Kernels", Duke University. PhD dissertation, Chapter 3 and Wolpert, R. L, Clyde, M.A, and Tu, C. (2011) "Stochastic Expansions with Continuous Dictionaries Levy Adaptive Regression Kernels, Annals of Statistics Vol (39) pages 1916-1962 <doi:10.1214/11-AOS889>.

Comprehensive toolkit for valid spatial, temporal, and grouped model evaluation. Automatically detects data dependencies (spatial autocorrelation, temporal structure, clustered observations), generates appropriate cross-validation schemes (spatial blocking, checkerboard, hexagonal, KNNDM, environmental blocking, leave-location-out, purged CV), and validates evaluation pipelines for leakage. Includes area of applicability (AOA) assessment following Meyer & Pebesma (2021) <doi:10.1111/2041-210X.13650>, forward feature selection with blocked CV, spatial thinning, block-permutation variable importance, extrapolation detection, and interactive visualizations. Integrates with tidymodels', caret', mlr3', ENMeval', and biomod2'. Based on evaluation principles described in Roberts et al. (2017) <doi:10.1111/ecog.02881>, Kaufman et al. (2012) <doi:10.1145/2382577.2382579>, Kapoor & Narayanan (2023) <doi:10.1016/j.patter.2023.100804>, and Linnenbrink et al. (2024) <doi:10.5194/gmd-17-5897-2024>.

Platform dedicated to the Global Modelling technique. Its aim is to obtain ordinary differential equations of polynomial form directly from time series. It can be applied to single or multiple time series under various conditions of noise, time series lengths, sampling, etc. This platform is developped at the Centre d'Etudes Spatiales de la Biosphere (CESBIO), UMR 5126 UPS/CNRS/CNES/IRD, 18 av. Edouard Belin, 31401 TOULOUSE, FRANCE. The developments were funded by the French program Les Enveloppes Fluides et l'Environnement (LEFE, MANU, projets GloMo, SpatioGloMo and MoMu). The French program Defi InFiNiTi (CNRS) and PNTS are also acknowledged (projects Crops'IChaos and Musc & SlowFast). The method is described in the article : Mangiarotti S. and Huc M. (2019) <doi:10.1063/1.5081448>.

This package provides tools for estimating causal effects in panel data using counterfactual methods, as well as other modern DID estimators. It is designed for causal panel analysis with binary treatments under the parallel trends assumption. The package supports scenarios where treatments can switch on and off and allows for limited carryover effects. It includes several imputation estimators, such as Gsynth (Xu 2017), linear factor models, and the matrix completion method. Detailed methodology is described in Liu, Wang, and Xu (2024) <doi:10.48550/arXiv.2107.00856> and Chiu et al. (2025) <doi:10.48550/arXiv.2309.15983>. Optionally integrates with the "HonestDiDFEct" package for sensitivity analyses compatible with imputation estimators. "HonestDiDFEct" is not on CRAN but can be obtained from <https://github.com/lzy318/HonestDiDFEct>.

An algorithm that trains a meta-learning procedure that combines screening and wrapper methods to find a set of extremely low-dimensional attribute combinations. This package works on top of the caret package and proceeds in a forward-step manner. More specifically, it builds and tests learners starting from very few attributes until it includes a maximal number of attributes by increasing the number of attributes at each step. Hence, for each fixed number of attributes, the algorithm tests various (randomly selected) learners and picks those with the best performance in terms of training error. Throughout, the algorithm uses the information coming from the best learners at the previous step to build and test learners in the following step. In the end, it outputs a set of strong low-dimensional learners.

Time Series Qn is a package with applications of the Qn estimator of Rousseeuw and Croux (1993) <doi:10.1080/01621459.1993.10476408> to univariate and multivariate Time Series in time and frequency domains. More specifically, the robust estimation of autocorrelation or autocovariance matrix functions from Ma and Genton (2000, 2001) <doi:10.1111/1467-9892.00203>, <doi:10.1006/jmva.2000.1942> and Cotta (2017) <doi:10.13140/RG.2.2.14092.10883> are provided. The robust pseudo-periodogram of Molinares et. al. (2009) <doi:10.1016/j.jspi.2008.12.014> is also given. This packages also provides the M-estimator of the long-memory parameter d based on the robustification of the GPH estimator proposed by Reisen et al. (2017) <doi:10.1016/j.jspi.2017.02.008>.