This package provides functions developed within Breeding Insight to analyze diploid and polyploid breeding and genetic data. BIGr provides the ability to filter variant call format (VCF) files, extract single nucleotide polymorphisms (SNPs) from diversity arrays technology missing allele discovery count (DArT MADC) files, and manipulate genotype data for both diploid and polyploid species. It also serves as the core dependency for the BIGapp Shiny app, which provides a user-friendly interface for performing routine genotype analysis tasks such as dosage calling, filtering, principal component analysis (PCA), genome-wide association studies (GWAS), and genomic prediction. For more details about the included breedTools functions, see Funkhouser et al. (2017) <doi:10.2527/tas2016.0003>, and the updog output format, see Gerard et al. (2018) <doi:10.1534/genetics.118.301468>.

Sequential Monte Carlo (SMC) inference for fully Bayesian Gaussian process (GP) regression and classification models by particle learning (PL) following Gramacy & Polson (2011) <doi:10.48550/arXiv.0909.5262>. The sequential nature of inference and the active learning (AL) hooks provided facilitate thrifty sequential design (by entropy) and optimization (by improvement) for classification and regression models, respectively. This package essentially provides a generic PL interface, and functions (arguments to the interface) which implement the GP models and AL heuristics. Functions for a special, linked, regression/classification GP model and an integrated expected conditional improvement (IECI) statistic provide for optimization in the presence of unknown constraints. Separable and isotropic Gaussian, and single-index correlation functions are supported. See the examples section of ?plgp and demo(package="plgp") for an index of demos.

To help French students from scientific preparatory classes for the Grandes Ecoles (CPGE) in their choice of field of study and career options, this package provides an interactive tool and data visualization of a graph clustered by different competitive exams and sectors of activity for French selective engineering schools and selective higher education institutions like Ecoles Normales Superieures (ENS) or specialized university programs (magisteres). Besides, there are two drop-down menus to select on the graph many fields or more than 200 engineering schools or ENS or magisteres. It gives the opportunity to expand, collapse clusters of selective exams interactively too. For more information, see the demonstration video: <https://valerierobert-maths.re/index.php/maths-en-cpge/>. The data was collected via the official French website: <https://www.scei-concours.fr/statistiques.html>.

It contains six common multi-category classification accuracy evaluation measures. All of these measures could be found in Li and Ming (2019) <doi:10.1002/sim.8103>. Specifically, Hypervolume Under Manifold (HUM), described in Li and Fine (2008) <doi:10.1093/biostatistics/kxm050>. Correct Classification Percentage (CCP), Integrated Discrimination Improvement (IDI), Net Reclassification Improvement (NRI), R-Squared Value (RSQ), described in Li, Jiang and Fine (2013) <doi:10.1093/biostatistics/kxs047>. Polytomous Discrimination Index (PDI), described in Van Calster et al. (2012) <doi:10.1007/s10654-012-9733-3>. Li et al. (2018) <doi:10.1177/0962280217692830>. PDI with variance estimation using Dover et al. (2021) <doi:10.1002/sim.9187>. We described all these above measures and our mcca package in Li, Gao and D'Agostino (2019) <doi:10.1002/sim.8103>.

Setup, run and analyze NetLogo (<https://www.netlogo.org>) model simulations in R'. nlrx experiments use a similar structure as NetLogos Behavior Space experiments. However, nlrx offers more flexibility and additional tools for running and analyzing complex simulation designs and sensitivity analyses. The user defines all information that is needed in an intuitive framework, using class objects. Experiments are submitted from R to NetLogo via XML files that are dynamically written, based on specifications defined by the user. By nesting model calls in future environments, large simulation design with many runs can be executed in parallel. This also enables simulating NetLogo experiments on remote high performance computing machines. In order to use this package, Java and NetLogo (>= 5.3.1) need to be available on the executing system.

Most price indexes are made with a two-step procedure, where period-over-period elementary indexes are first calculated for a collection of elementary aggregates at each point in time, and then aggregated according to a price index aggregation structure. These indexes can then be chained together to form a time series that gives the evolution of prices with respect to a fixed base period. This package contains a collection of functions that revolve around this work flow, making it easy to build standard price indexes, and implement the methods described by Balk (2008, <doi:10.1017/CBO9780511720758>), von der Lippe (2007, <doi:10.3726/978-3-653-01120-3>), and the CPI manual (2020, <doi:10.5089/9781484354841.069>) and PPI manual (2004, <doi:10.5089/9781589063044.069>) for bilateral price indexes.

An increasing number of microbiome datasets have been generated and analyzed with the help of rapidly developing sequencing technologies. At present, analysis of taxonomic profiling data is mainly conducted using composition-based methods, which ignores interactions between community members. Besides this, a lack of efficient ways to compare microbial interaction networks limited the study of community dynamics. To better understand how community diversity is affected by complex interactions between its members, we developed a framework (Microbial community dIversity and Network Analysis, mina), a comprehensive framework for microbial community diversity analysis and network comparison. By defining and integrating network-derived community features, we greatly reduce noise-to-signal ratio for diversity analyses. A bootstrap and permutation-based method was implemented to assess community network dissimilarities and extract discriminative features in a statistically principled way.

This package provides a suite of tools to mitigate sampling bias in species occurrence records by thinning data in the environmental space (E-space). This process can improve the accuracy and precision of species distribution models (SDM, also known as ecological niche models, ENM). The package offers a data-driven protocol to determine thinning parameters using kernel-density bandwidth selection. Two thinning methods are provided (stochastic and deterministic) to reduce over-sampled environmental conditions and down-weight outlier observations. The name bean reflects the core principle of the method: each pod (a grid cell in E-space) is allowed to contain only a limited number of beans (occurrence points). See Silverman (1986, ISBN:978-0-412-24620-3) and Rousseeuw and Leroy (2003, ISBN:978-0-471-48855-2) for the underlying statistical methods.

Reads the versioned exchange files written by the Zotero plugins zotQDA and qdaZ -- coded fragments, code systems, coding histories and team-consensus results -- validates them against the shipped contract, and reproduces the plugin's graphics with ggplot2'. Adds what those plugins deliberately leave out: six agreement coefficients with bootstrap confidence intervals, the reliability of the segmentation itself, chi-squared tests of code by group tables with effect sizes, correspondence analysis, multidimensional scaling and hierarchical clustering of codes. Projects from other programs can be read through the REFI-QDA interchange standard <https://www.qdasoftware.org/>, which makes those analyses available to users of established software that does not offer them; the subset a .qdpx supports is reported on import. Reference files are included, so every function can be tried without a Zotero installation.

Subgroup classification is a basic task in genomic data analysis, especially for gene expression and DNA methylation data analysis. It can also be used to test the agreement to known clinical annotations, or to test whether there exist significant batch effects. The cola package provides a general framework for subgroup classification by consensus partitioning. It has the following features: 1. It modularizes the consensus partitioning processes that various methods can be easily integrated. 2. It provides rich visualizations for interpreting the results. 3. It allows running multiple methods at the same time and provides functionalities to straightforward compare results. 4. It provides a new method to extract features which are more efficient to separate subgroups. 5. It automatically generates detailed reports for the complete analysis. 6. It allows applying consensus partitioning in a hierarchical manner.

Find multiple solutions of a nonlinear least squares problem. Cluster Gauss-Newton method does not assume uniqueness of the solution of the nonlinear least squares problem and compute multiple minimizers. Please cite the following paper when this software is used in your research: Aoki et al. (2020) <doi:10.1007/s11081-020-09571-2>. Cluster Gaussâ Newton method. Optimization and Engineering, 1-31. Please cite the following paper when profile likelihood plot is drawn with this software and used in your research: Aoki and Sugiyama (2024) <doi:10.1002/psp4.13055>. Cluster Gauss-Newton method for a quick approximation of profile likelihood: With application to physiologically-based pharmacokinetic models. CPT Pharmacometrics Syst Pharmacol.13(1):54-67. GPT based helper bot available at <https://chatgpt.com/g/g-684936db9e748191a2796debb00cd755-cluster-gauss-newton-method-helper-bot> .

This package implements Multivariate Quantile-on-Quantile Regression (m-QQR) of Sinha, Ghosh, Hussain, Nguyen and Das (2023) <doi:10.1016/j.eneco.2023.107021>, extending the bivariate Quantile-on-Quantile regression of Sim and Zhou (2015) <doi:10.1016/j.jbankfin.2015.01.013> to include exogenous moderators and controls with optional interaction terms. For each pair of quantile levels (theta of the response and tau of the regressor) the package fits a locally-weighted quantile regression of y on the principal regressor x, a lagged dependent variable, moderators Z and the x*Z interaction terms, using Gaussian kernel weights on the empirical cumulative distribution function (CDF) distance. Bootstrap standard errors and Koenker-Machado pseudo R-squared are reported. Visualisations include MATLAB'-style Parula and Jet 3D surfaces, heatmaps and contour plots through plotly'.

The Behavioral Change Point Analysis (BCPA) is a method of identifying hidden shifts in the underlying parameters of a time series, developed specifically to be applied to animal movement data which is irregularly sampled. The method is based on: E. Gurarie, R. Andrews and K. Laidre A novel method for identifying behavioural changes in animal movement data (2009) Ecology Letters 12:5 395-408. A development version is on <https://github.com/EliGurarie/bcpa>. NOTE: the BCPA method may be useful for any univariate, irregularly sampled Gaussian time-series, but animal movement analysts are encouraged to apply correlated velocity change point analysis as implemented in the smoove package, as of this writing on GitHub at <https://github.com/EliGurarie/smoove>. An example of a univariate analysis is provided in the UnivariateBCPA vignette.

Spatial heterogeneity can be specified in various ways. hspm is an ambitious project that aims at implementing various methodologies to control for heterogeneity in spatial models. The current version of hspm deals with spatial and (non-spatial) regimes models. In particular, the package allows to estimate a general spatial regimes model with additional endogenous variables, specified in terms of a spatial lag of the dependent variable, the spatially lagged regressors, and, potentially, a spatially autocorrelated error term. Spatial regime models are estimated by instrumental variables and generalized methods of moments (see Arraiz et al., (2010) <doi:10.1111/j.1467-9787.2009.00618.x>, Bivand and Piras, (2015) <doi:10.18637/jss.v063.i18>, Drukker et al., (2013) <doi:10.1080/07474938.2013.741020>, Kelejian and Prucha, (2010) <doi:10.1016/j.jeconom.2009.10.025>).

Implemented here are procedures for fitting hierarchical generalized linear models (HGLM). It can be used for linear mixed models and generalized linear mixed models with random effects for a variety of links and a variety of distributions for both the outcomes and the random effects. Fixed effects can also be fitted in the dispersion part of the mean model. As statistical models, HGLMs were initially developed by Lee and Nelder (1996) <https://www.jstor.org/stable/2346105?seq=1>. We provide an implementation (Ronnegard, Alam and Shen 2010) <https://journal.r-project.org/archive/2010-2/RJournal_2010-2_Roennegaard~et~al.pdf> following Lee, Nelder and Pawitan (2006) <ISBN: 9781420011340> with algorithms extended for spatial modeling (Alam, Ronnegard and Shen 2015) <https://journal.r-project.org/archive/2015/RJ-2015-017/RJ-2015-017.pdf>.

This package implements hierarchical Bayesian inference, robust frequentist inference, and distribution-free inference for dependent and unbalanced data under strong-mixing conditions. Supports triangular-array, weighted-sum and mixingale convergence regimes with Whittle and composite likelihoods, heteroskedasticity-and-autocorrelation-consistent variance estimation, block bootstrap with automatic block length, fixed-bandwidth HAR inference, adaptive conformal prediction, Bayesian decision under Region of Practical Equivalence, bridge-sampling Bayes factors, and predictive comparison via the Widely Applicable Information Criterion and leave-future-out cross-validation. Methods follow Andrews (1991) <doi:10.2307/2938229>, Kiefer and Vogelsang (2005) <doi:10.1017/S0266466605050565>, Patton, Politis and White (2009) <doi:10.1080/07474930802459016>, Vehtari, Gelman and Gabry (2017) <doi:10.1007/s11222-016-9696-4>, Kruschke (2018) <doi:10.1177/2515245918771304>, and Gibbs and Candes (2021) <doi:10.48550/arXiv.2106.00170>.

This package provides a phenotype-aware algorithm for resolving cryptic relatedness in genetic studies. It removes related individuals based on kinship or identity-by-descent (IBD) scores while prioritizing subjects with phenotypes of interest. This approach helps maximize the retention of informative subjects, particularly for rare or valuable traits, and improves statistical power in genetic and epidemiological studies. KDPS supports both categorical and quantitative phenotypes, composite scoring, and customizable pruning strategies using a fuzziness parameter. Benchmark results show improved phenotype retention and high computational efficiency on large-scale datasets like the UK Biobank. Methods used include Manichaikul et al. (2010) <doi:10.1093/bioinformatics/btq559> for kinship estimation, Purcell et al. (2007) <doi:10.1086/519795> for IBD estimation, and Bycroft et al. (2018) <doi:10.1038/s41586-018-0579-z> for UK Biobank data reference.

This package offers a robust approach to make inference on the association of covariates with the absolute abundance (AA) of microbiome in an ecosystem. It can be also directly applied to relative abundance (RA) data to make inference on AA because the ratio of two RA is equal to the ratio of their AA. This algorithm can estimate and test the associations of interest while adjusting for potential confounders. The estimates of this method have easy interpretation like a typical regression analysis. High-dimensional covariates are handled with regularization and it is implemented by parallel computing. False discovery rate is automatically controlled by this approach. Zeros do not need to be imputed by a positive value for the analysis. The IFAA package also offers the MZILN function for estimating and testing associations of abundance ratios with covariates.

The cito package provides a user-friendly interface for training and interpreting deep neural networks (DNN). cito simplifies the fitting of DNNs by supporting the familiar formula syntax, hyperparameter tuning under cross-validation, and helps to detect and handle convergence problems. DNNs can be trained on CPU, GPU and MacOS GPUs. In addition, cito has many downstream functionalities such as various explainable AI (xAI) metrics (e.g. variable importance, partial dependence plots, accumulated local effect plots, and effect estimates) to interpret trained DNNs. cito optionally provides confidence intervals (and p-values) for all xAI metrics and predictions. At the same time, cito is computationally efficient because it is based on the deep learning framework torch'. The torch package is native to R, so no Python installation or other API is required for this package.

Fit Bayesian (hierarchical) cognitive models using a linear modeling language interface using particle Metropolis Markov chain Monte Carlo sampling with Gibbs steps. The diffusion decision model (DDM), linear ballistic accumulator model (LBA), racing diffusion model (RDM), and the lognormal race model (LNR) are supported. Additionally, users can specify their own likelihood function and/or choose for non-hierarchical estimation, as well as for a diagonal, blocked or full multivariate normal group-level distribution to test individual differences. Prior specification is facilitated through methods that visualize the (implied) prior. A wide range of plotting functions assist in assessing model convergence and posterior inference. Models can be easily evaluated using functions that plot posterior predictions or using relative model comparison metrics such as information criteria or Bayes factors. References: Stevenson et al. (2024) <doi:10.31234/osf.io/2e4dq>.

This is a utility for transforming Ecological Metadata Language ('EML') files into JSON-LD and back into EML. Doing so creates a list-based representation of EML in R, so that EML data can easily be manipulated using standard R tools. This makes this package an effective backend for other R'-based tools working with EML. By abstracting away the complexity of XML Schema, developers can build around native R list objects and not have to worry about satisfying many of the additional constraints of set by the schema (such as element ordering, which is handled automatically). Additionally, the JSON-LD representation enables the use of developer-friendly JSON parsing and serialization that may facilitate the use of EML in contexts outside of R, as well as the informatics-friendly serializations such as RDF and SPARQL queries.

This package implements Higher-Order Influence Function (HOIF) estimators of the Average Treatment Effect (ATE), following Robins et al. (2008) <doi:10.1214/193940307000000527>, Liu et al. (2017) <doi:10.48550/arXiv.1705.07577> and Liu and Li (2023) <doi:10.48550/arXiv.2302.08097>. Estimators of any order are supported, with optional covariate basis transformations (B-splines, Fourier) and optional K-fold sample splitting (cross-fitting) for improved finite-sample performance. The core higher-order U-statistics are computed exactly via the ustats package, an R interface to the Python package u-stats'; the underlying algorithm and its computational complexity are analyzed in Chen, Zhang and Liu (2025) <doi:10.48550/arXiv.2508.12627>. A pure R implementation (up to order 6) is also provided as a fallback that does not require Python'.

The itdr() routine allows for the estimation of sufficient dimension reduction subspaces in univariate regression such as the central mean subspace or central subspace in regression. This is achieved using Fourier transformation methods proposed by Zhu and Zeng (2006) <doi:10.1198/016214506000000140>, convolution transformation methods proposed by Zeng and Zhu (2010) <doi:10.1016/j.jmva.2009.08.004>, and iterative Hessian transformation methods proposed by Cook and Li (2002) <doi:10.1214/aos/1021379861>. Additionally, mitdr() function provides optimal estimators for sufficient dimension reduction subspaces in multivariate regression by optimizing a discrepancy function using a Fourier transform approach proposed by Weng and Yin (2022) <doi:10.5705/ss.202020.0312>, and selects the sufficient variables using Fourier transform sparse inverse regression estimators proposed by Weng (2022) <doi:10.1016/j.csda.2021.107380>.

User-friendly general package providing standard methods for meta-analysis and supporting Schwarzer, Carpenter, and Rücker <DOI:10.1007/978-3-319-21416-0>, "Meta-Analysis with R" (2015): - common effect and random effects meta-analysis; - several plots (forest, funnel, Galbraith / radial, L'Abbe, Baujat, bubble); - three-level meta-analysis model; - generalised linear mixed model; - logistic regression with penalised likelihood for rare events; - Hartung-Knapp method for random effects model; - Kenward-Roger method for random effects model; - prediction interval and density of the prediction distribution; - expected proportion of comparable studies with clinically important benefit or harm; - statistical tests for funnel plot asymmetry; - trim-and-fill method to evaluate bias in meta-analysis; - meta-regression; - cumulative meta-analysis and leave-one-out meta-analysis; - import data from RevMan 5'; - produce forest plot summarising several (subgroup) meta-analyses.