Lactation curves describe temporal changes in milk yield and are key to breeding and managing dairy animals more efficiently. The use of ensemble modeling, which consists of combining predictions from multiple models, has the potential to yields more accurate and robust estimates of lactation patterns than relying solely on single model estimates. The package EMOTIONS fits 47 models for lactation curves and creates ensemble models using model averaging based on Akaike information criterion (AIC), Bayesian information criterion (BIC), root mean square percentage error (RMSPE) and mean squared error (MAE), variance of the predictions, cosine similarity for each model's predictions, and Bayesian Model Average (BMA). The daily production values predicted through the ensemble models can be used to estimate resilience indicators in the package. The package allows the graphical visualization of the model ranks and the predicted lactation curves. Additionally, the packages allows the user to detect milk loss events and estimate residual-based resilience indicators.

This package provides automated statistical analysis, rich visualization, and multi-format narrative reporting through a unified pipeline. Descriptive statistics are available via easy_describe() and easy_group_summary(). Inferential tests with plain-language narratives are provided by easy_regression(), easy_logistic_regression(), easy_ttest(), easy_anova(), easy_chisq(), easy_ztest(), easy_ftest(), easy_correlation(), easy_wilcox(), and easy_kruskal(). Publication-ready ggplot2 visualizations are produced by easy_histogram(), easy_boxplot(), easy_scatter(), easy_barplot(), easy_qqplot(), easy_density(), easy_correlation_heatmap(), easy_regression_diagnostics(), and easy_odds_ratio_plot(). The core Narrative Generator Module applies conditional logic to extracted p-values, effect sizes, and model-fit metrics to produce statistically sound, human-readable explanations automatically. Results render in the RStudio Viewer (HTML), the console (ASCII), or export directly to Microsoft Word via flextable and officer'.

This package provides tools for AI-assisted qualitative data coding using large language models ('LLMs') via the ellmer package, supporting providers including OpenAI', Anthropic', Google', Azure', and local models via Ollama'. Provides a codebook'-based workflow for defining coding instructions and applying them to texts, images, audio recordings, and other data. Includes built-in codebooks for common applications such as sentiment analysis and policy coding, and functions for creating custom codebooks for specific research questions. Supports systematic replication across models and settings, computing inter-coder reliability statistics including Krippendorff's alpha (Krippendorff 2019, <doi:10.4135/9781071878781>) and Fleiss kappa (Fleiss 1971, <doi:10.1037/h0031619>), as well as gold-standard validation metrics including accuracy, precision, recall, and F1 scores following Sokolova and Lapalme (2009, <doi:10.1016/j.ipm.2009.03.002>). Provides audit trail functionality for documenting coding workflows following Lincoln and Guba's (1985, ISBN:0803924313) framework for establishing trustworthiness in qualitative research.

This package implements a general algorithm for estimating Sparse Multiple Index (SMI) models for nonparametric forecasting and prediction. Estimation of SMI models requires the Gurobi mixed integer programming (MIP) solver via the gurobi R package. To use this functionality, the Gurobi Optimizer must be installed, and a valid license obtained and activated from <https://www.gurobi.com>. The gurobi R package must then be installed and configured following the instructions at <https://support.gurobi.com/hc/en-us/articles/14462206790033-How-do-I-install-Gurobi-for-R>. The package also includes functions for fitting nonparametric additive models with backward elimination, group-wise additive index models, and projection pursuit regression models as benchmark comparison methods. In addition, it provides tools for generating prediction intervals to quantify uncertainty in point forecasts produced by the SMI model and benchmark models, using the classical block bootstrap and a new method called conformal bootstrap, which integrates block bootstrap with split conformal prediction.

Generation of domain variables, linearization of several non-linear population statistics (the ratio of two totals, weighted income percentile, relative median income ratio, at-risk-of-poverty rate, at-risk-of-poverty threshold, Gini coefficient, gender pay gap, the aggregate replacement ratio, the relative median income ratio, median income below at-risk-of-poverty gap, income quintile share ratio, relative median at-risk-of-poverty gap), computation of regression residuals in case of weight calibration, variance estimation of sample surveys by the ultimate cluster method (Hansen, Hurwitz and Madow, Sample Survey Methods And Theory, vol. I: Methods and Applications; vol. II: Theory. 1953, New York: John Wiley and Sons), variance estimation for longitudinal, cross-sectional measures and measures of change for single and multistage stage cluster sampling designs (Berger, Y. G., 2015, <doi:10.1111/rssa.12116>). Several other precision measures are derived - standard error, the coefficient of variation, the margin of error, confidence interval, design effect.

Programmatic access to the microdata of the Bolivian population and housing censuses of 1976, 1992, 2001, 2012 and 2024, published by the National Statistics Institute of Bolivia (INE, <https://www.ine.gob.bo/>). Data files in Apache Parquet format are downloaded on demand from a companion data repository, cached locally, and can be filtered by department, province or municipality. Supports dplyr workflows through Apache Arrow and SQL queries through DuckDB'. Includes variable dictionaries for every census year with a thematic taxonomy and contextual metadata (reference population, questionnaire item number and provenance of each variable), derived from the census questionnaires and from the Data Documentation Initiative (DDI) files of the INE ANDA catalogue; functions to harmonise variables across censuses for temporal comparison; and choropleth maps at the department and municipality level. Also includes the 2024 census aggregates for urban blocks and rural communities, with their geometries. Documentation and messages are in Spanish, the language of the source data.

Digital simulation of electrochemical processes. Each function allows for implicit and explicit solution of the differential equation using methods like Euler, Backwards implicit, Runge Kutta 4, Crank Nicholson and Backward differentiation formula as well as different number of points for derivative approximation. Several electrochemical processes can be simulated such as: Chronoamperometry, Potential Step, Linear Sweep, Cyclic Voltammetry, Cyclic Voltammetry with electrochemical reaction followed by chemical reaction (EC mechanism) and CV with two following electrochemical reaction (EE mechanism). In update 1.1.0 has been added a general purpose CV function that allow to simulate up to 4 EE mechanism combined with chemical reaction for each species.Update 1.2.0 improved the accuracy of the measurements and allow personalized data resolution for simulation. Bibliography regarding this methods can be found in the following texts. Dieter Britz, Jorg Strutwolf (2016) <ISBN:978-3-319-30292-8>. Allen J. Bard, Larry R. Faulkner (2000) <ISBN:978-0-471-04372-0>.

For emulating multifidelity computer models. The major methods include univariate autoregressive cokriging and multivariate autoregressive cokriging. The autoregressive cokriging methods are implemented for both hierarchically nested design and non-nested design. For hierarchically nested design, the model parameters are estimated via standard optimization algorithms; For non-nested design, the model parameters are estimated via Monte Carlo expectation-maximization (MCEM) algorithms. In both cases, the priors are chosen such that the posterior distributions are proper. Notice that the uniform priors on range parameters in the correlation function lead to improper posteriors. This should be avoided when Bayesian analysis is adopted. The development of objective priors for autoregressive cokriging models can be found in Pulong Ma (2020) <DOI:10.1137/19M1289893>. The development of the multivariate autoregressive cokriging models with possibly non-nested design can be found in Pulong Ma, Georgios Karagiannis, Bledar A Konomi, Taylor G Asher, Gabriel R Toro, and Andrew T Cox (2022) <DOI:10.1111/rssc.12558>.

This package provides tools for analyzing and optimizing PTSD (Post-Traumatic Stress Disorder) diagnostic criteria using PCL-5 (PTSD Checklist for DSM-5) and CAPS-5 (Clinician-Administered PTSD Scale for DSM-5) data. Functions identify optimal subsets of PCL-5 items that maintain diagnostic accuracy while reducing assessment burden. Includes tools for both hierarchical (cluster-based) and non-hierarchical symptom combinations, calculation of diagnostic metrics, and comparison with standard DSM-5 criteria. Redundancy analysis quantifies how many item subsets perform equivalently, through plateau sizes and bootstrap stability, and reports item selection against the chance baseline of the searched candidate space. A transport layer allows a site to evaluate subsets derived elsewhere and return only aggregate summaries, supporting multi-site validation without sharing individual-level data. Model validation is conducted using holdout and cross-validation methods to assess robustness and generalizability of the results. For more details see Weidmann et al. (2025) <doi:10.31219/osf.io/6rk72_v1>.

This R-extension package contains dozens of functions useful for: database style joins [nerge()] & aggregation [bestBy(), groupBy() & regroup()], database migration [dbWriteTable2()], file I/O [write.delim(), read.tab()], text parsing / data mining [m()], data structure conversion [nv(), tab2df()], summarizing & reporting [pct(), fit.1ln.rprt()], character string manipulation [m() & pad()], legend table making [sstable() & leghead()] & plot placement [legend.position()], plot annotation [labsegs() & mvlabs()], data visualization [pies(), spie(), & heatmatrix()], and data exploration [hyperplot(), plot.xy.ab.p()], batch scripting [parseArgString()]. The package's greatest contributions stem from its database style merge, aggregation and interface functions as well as in it's extensive use and propagation of row, column and vector names in most functions. The latest additions are plotting functions [confound.grid() & sparge()] that intake a dataframe & formulas to visually resolve variable confounding (Simpson, 1951).

Design and evaluate choice-based conjoint survey experiments. Generate a variety of survey designs, including random designs, frequency-based designs, and D-optimal designs, as well as "labeled" designs (also known as "alternative-specific designs"), designs with "no choice" options, and designs with dominant alternatives removed. Conveniently inspect and compare designs using a variety of metrics, including design balance, overlap, and D-error, and simulate choice data for a survey design either randomly or according to a utility model defined by user-provided prior parameters. Conduct a power analysis for a given survey design by estimating the same model on different subsets of the data to simulate different sample sizes. Bayesian D-efficient designs using the cea and modfed methods are obtained using the idefix package by Traets et al (2020) <doi:10.18637/jss.v096.i03>. Choice simulation and model estimation in power analyses are handled using the logitr package by Helveston (2023) <doi:10.18637/jss.v105.i10>.

Easily compute education inequality measures and the distribution of educational attainments for any group of countries, using the data set developed in Jorda, V. and Alonso, JM. (2017) <DOI:10.1016/j.worlddev.2016.10.005>. The package offers the possibility to compute not only the Gini index, but also generalized entropy measures for different values of the sensitivity parameter. In particular, the package includes functions to compute the mean log deviation, which is more sensitive to the bottom part of the distribution; the Theilâ s entropy measure, equally sensitive to all parts of the distribution; and finally, the GE measure when the sensitivity parameter is set equal to 2, which gives more weight to differences in higher education. The decomposition of these measures in the components between-country and within-country inequality is also provided. Two graphical tools are also provided, to analyse the evolution of the distribution of educational attainments: The cumulative distribution function and the Lorenz curve.

It implements a hybrid spatial model for improved spatial prediction by combining the variable selection capability of LASSO (Least Absolute Shrinkage and Selection Operator) with the Geographically Weighted Regression (GWR) model that captures the spatially varying relationship efficiently. For method details see, Wheeler, D.C.(2009).<DOI:10.1068/a40256>. The developed hybrid model efficiently selects the relevant variables by using LASSO as the first step; these selected variables are then incorporated into the GWR framework, allowing the estimation of spatially varying regression coefficients at unknown locations and finally predicting the values of the response variable at unknown test locations while taking into account the spatial heterogeneity of the data. Integrating the LASSO and GWR models enhances prediction accuracy by considering spatial heterogeneity and capturing the local relationships between the predictors and the response variable. The developed hybrid spatial model can be useful for spatial modeling, especially in scenarios involving complex spatial patterns and large datasets with multiple predictor variables.

Designs plots in terms of core structure. See example(metaplot)'. Primary arguments are (unquoted) column names; order and type (numeric or not) dictate the resulting plot. Specify any y variables, x variable, any groups variable, and any conditioning variables to metaplot() to generate density plots, boxplots, mosaic plots, scatterplots, scatterplot matrices, or conditioned plots. Use multiplot() to arrange plots in grids. Wherever present, scalar column attributes label and guide are honored, producing fully annotated plots with minimal effort. Attribute guide is typically units, but may be encoded() to provide interpretations of categorical values (see ?encode'). Utility unpack() transforms scalar column attributes to row values and pack() does the reverse, supporting tool-neutral storage of metadata along with primary data. The package supports customizable aesthetics such as such as reference lines, unity lines, smooths, log transformation, and linear fits. The user may choose between trellis and ggplot output. Compact syntax and integrated metadata promote workflow scalability.

We propose a procedure for sample size calculation while controlling false discovery rate for RNA-seq experimental design. Our procedure depends on the Voom method proposed for RNA-seq data analysis by Law et al. (2014) <DOI:10.1186/gb-2014-15-2-r29> and the sample size calculation method proposed for microarray experiments by Liu and Hwang (2007) <DOI:10.1093/bioinformatics/btl664>. We develop a set of functions that calculates appropriate sample sizes for two-sample t-test for RNA-seq experiments with fixed or varied set of parameters. The outputs also contain a plot of power versus sample size, a table of power at different sample sizes, and a table of critical test values at different sample sizes. To install this package, please use source("http://bioconductor.org/biocLite.R"); biocLite("ssizeRNA")'. For R version 3.5 or greater, please use if(!requireNamespace("BiocManager", quietly = TRUE))install.packages("BiocManager"); BiocManager::install("ssizeRNA")'.

This package can do non-parametric bootstrap and permutation resampling-based multiple testing procedures (including empirical Bayes methods) for controlling the family-wise error rate (FWER), generalized family-wise error rate (gFWER), tail probability of the proportion of false positives (TPPFP), and false discovery rate (FDR). Several choices of bootstrap-based null distribution are implemented (centered, centered and scaled, quantile-transformed). Single-step and step-wise methods are available. Tests based on a variety of T- and F-statistics (including T-statistics based on regression parameters from linear and survival models as well as those based on correlation parameters) are included. When probing hypotheses with T-statistics, users may also select a potentially faster null distribution which is multivariate normal with mean zero and variance covariance matrix derived from the vector influence function. Results are reported in terms of adjusted P-values, confidence regions and test statistic cutoffs. The procedures are directly applicable to identifying differentially expressed genes in DNA microarray experiments.

Cell surface proteins form a major fraction of the druggable proteome and can be used for tissue-specific delivery of oligonucleotide/cell-based therapeutics. Alternatively spliced surface protein isoforms have been shown to differ in their subcellular localization and/or their transmembrane (TM) topology. Surface proteins are hydrophobic and remain difficult to study thereby necessitating the use of TM topology prediction methods such as TMHMM and Phobius. However, there exists a need for bioinformatic approaches to streamline batch processing of isoforms for comparing and visualizing topologies. To address this gap, we have developed an R package, surfaltr. It pairs inputted isoforms, either known alternatively spliced or novel, with their APPRIS annotated principal counterparts, predicts their TM topologies using TMHMM or Phobius, and generates a customizable graphical output. Further, surfaltr facilitates the prioritization of biologically diverse isoform pairs through the incorporation of three different ranking metrics and through protein alignment functions. Citations for programs mentioned here can be found in the vignette.

Software of esDesign is developed to implement the adaptive enrichment designs with sample size re-estimation presented in Lin et al. (2021) <doi: 10.1016/j.cct.2020.106216>. In details, three-proposed trial designs are provided, including the AED1-SSR (or ES1-SSR), AED2-SSR (or ES2-SSR) and AED3-SSR (or ES3-SSR). In addition, this package also contains several widely used adaptive designs, such as the Marker Sequential Test (MaST) design proposed Freidlin et al. (2014) <doi:10.1177/1740774513503739>, the adaptive enrichment designs without early stopping (AED or ES), the sample size re-estimation procedure (SSR) based on the conditional power proposed by Proschan and Hunsberger (1995), and some useful functions. In details, we can calculate the futility and/or efficacy stopping boundaries, the sample size required, calibrate the value of the threshold of the difference between subgroup-specific test statistics, conduct the simulation studies in AED, SSR, AED1-SSR, AED2-SSR and AED3-SSR.

We provide a non-parametric and a parametric approach to investigate the equivalence (or non-inferiority) of two survival curves, obtained from two given datasets. The test is based on the creation of confidence intervals at pre-specified time points. For the non-parametric approach, the curves are given by Kaplan-Meier curves and the variance for calculating the confidence intervals is obtained by Greenwood's formula. The parametric approach is based on estimating the underlying distribution, where the user can choose between a Weibull, Exponential, Gaussian, Logistic, Log-normal or a Log-logistic distribution. Estimates for the variance for calculating the confidence bands are obtained by a (parametric) bootstrap approach. For this bootstrap censoring is assumed to be exponentially distributed and estimates are obtained from the datasets under consideration. All details can be found in K.Moellenhoff and A.Tresch: Survival analysis under non-proportional hazards: investigating non-inferiority or equivalence in time-to-event data <arXiv:2009.06699>.

Given independent and identically distributed observations X(1), ..., X(n) from a density f, provides five methods to perform a multiscale analysis about f as well as the necessary critical values. The first method, introduced in Duembgen and Walther (2008), provides simultaneous confidence statements for the existence and location of local increases (or decreases) of f, based on all intervals I(all) spanned by any two observations X(j), X(k). The second method approximates the latter approach by using only a subset of I(all) and is therefore computationally much more efficient, but asymptotically equivalent. Omitting the additive correction term Gamma in either method offers another two approaches which are more powerful on small scales and less powerful on large scales, however, not asymptotically minimax optimal anymore. Finally, the block procedure is a compromise between adding Gamma or not, having intermediate power properties. The latter is again asymptotically equivalent to the first and was introduced in Rufibach and Walther (2010).

Detection of overdispersion in count data for multiple regression analysis. Log-linear count data regression is one of the most popular techniques for predictive modeling where there is a non-negative discrete quantitative dependent variable. In order to ensure the inferences from the use of count data models are appropriate, researchers may choose between the estimation of a Poisson model and a negative binomial model, and the correct decision for prediction from a count data estimation is directly linked to the existence of overdispersion of the dependent variable, conditional to the explanatory variables. Based on the studies of Cameron and Trivedi (1990) <doi:10.1016/0304-4076(90)90014-K> and Cameron and Trivedi (2013, ISBN:978-1107667273), the overdisp() command is a contribution to researchers, providing a fast and secure solution for the detection of overdispersion in count data. Another advantage is that the installation of other packages is unnecessary, since the command runs in the basic R language.

Simulate multivariate correlated data given nonparametric marginals and their joint structure characterized by a Pearson or Spearman correlation matrix. The simulator engages the problem from a purely computational perspective. It assumes no statistical models such as copulas or parametric distributions, and can approximate the target correlations regardless of theoretical feasibility. The algorithm integrates and advances the Iman-Conover (1982) approach <doi:10.1080/03610918208812265> and the Ruscio-Kaczetow iteration (2008) <doi:10.1080/00273170802285693>. Package functions are carefully implemented in C++ for squeezing computing speed, suitable for large input in a manycore environment. Precision of the approximation and computing speed both substantially outperform various CRAN packages to date. Benchmarks are detailed in function examples. A simple heuristic algorithm is additionally designed to optimize the joint distribution in the post-simulation stage. The heuristic demonstrated good potential of achieving the same level of precision of approximation without the enhanced Iman-Conover-Ruscio-Kaczetow. The package contains a copy of Permuted Congruential Generator.

Simple and efficient access to Yahoo Finance's screener API <https://finance.yahoo.com/research-hub/screener/> for querying and retrieval of financial data. The core functionality abstracts the complexities of interacting with Yahoo Finance APIs, such as session management, crumb and cookie handling, query construction, pagination, and JSON payload generation. This abstraction allows users to focus on filtering and retrieving data rather than managing API details. Use cases include screening across a range of security types including equities, mutual funds, ETFs, indices, and futures. The package supports advanced query capabilities, including logical operators, nested filters, and customizable payloads. It automatically handles pagination to ensure efficient retrieval of large datasets by fetching results in batches of up to 250 entries per request. Filters can be dynamically defined to accommodate a wide range of screening needs. The implementation leverages standard HTTP libraries to handle API interactions efficiently and provides support for both R and Python to ensure accessibility for a broad audience.

In screening programs, individuals are usually followed up and tested (screened) for the development of a disease, such as cancer. The target disease often develops progressively in stages; for example healthy (state 1), pre-state disease (state 2), and the disease state (state 3). When the pre-state disease is found during screening it is intervened upon, for example by surgical removal of a lesion, so that the progression of the pre-state disease to disease is interrupted. This is called censoring due to intervention. Researchers often want to estimate the time from baseline to the pre-state disease, the time from the pre-state disease to the disease, and the total time from baseline to the disease. In addition, researchers often want to regress these times on baseline covariates. To these ends, BayesTSM estimates a progressive three-state model with censoring due to intervention using Bayesian estimation methods, as described in Klausch et al. (2023) <doi:10.1214/22-AOAS1669>.