Designed for prediction error estimation through resampling techniques, possibly accelerated by parallel execution on a compute cluster. Newly developed model fitting routines can be easily incorporated. Methods used in the package are detailed in Porzelius Ch., Binder H. and Schumacher M. (2009) <doi:10.1093/bioinformatics/btp062> and were used, for instance, in Porzelius Ch., Schumacher M. and Binder H. (2011) <doi:10.1007/s00180-011-0236-6>.

Parametric bootstrap (PB) has been used for three-way ANOVA model with unequal group variances.

Piecewise constant hazard models for survival data. The package allows for right-censored, left-truncated, and interval-censored data.

This package provides functions to estimate and plot smooth or linear population trends, or population indices, from animal or plant count survey data.

Includes functions for keyword search of pdf files. There is also a wrapper that includes searching of all files within a single directory.

This package provides functionality for Bayesian analysis of replication studies using power prior approaches (Pawel et al., 2023) <doi:10.1007/s11749-023-00888-5>.

These are harmonized datasets produced as part of the Clinical Trials Network (CTN) protocol number 0094. This is a US National Institute of Drug Abuse (NIDA) funded project; to learn more go to <https://ctnlibrary.org/protocol/ctn0094/>. These are datasets which have the data harmonized from CTN-0027 (<https://ctnlibrary.org/protocol/ctn0027/>), CTN-0030 (<https://ctnlibrary.org/protocol/ctn0030/>), and CTN-0051 (<https://ctnlibrary.org/protocol/ctn0051/>).

Engineered features and "helper" functions ancillary to the public.ctn0094data package, extending this package for ease of use (see <https://CRAN.R-project.org/package=public.ctn0094data>). This public.ctn0094data package contains harmonized datasets from some of the National Institute of Drug Abuse's Clinical Trials Network (NIDA's CTN) projects. Specifically, the CTN-0094 project is to harmonize and de-identify clinical trials data from the CTN-0027, CTN-0030, and CTN-51 studies for opioid use disorder. This current version is built from public.ctn0094data v. 1.0.6.

Partitioning clustering divides the objects in a data set into non-overlapping subsets or clusters by using the prototype-based probabilistic and possibilistic clustering algorithms. This package covers a set of the functions for Fuzzy C-Means (Bezdek, 1974) <doi:10.1080/01969727308546047>, Possibilistic C-Means (Krishnapuram & Keller, 1993) <doi:10.1109/91.227387>, Possibilistic Fuzzy C-Means (Pal et al, 2005) <doi:10.1109/TFUZZ.2004.840099>, Possibilistic Clustering Algorithm (Yang et al, 2006) <doi:10.1016/j.patcog.2005.07.005>, Possibilistic C-Means with Repulsion (Wachs et al, 2006) <doi:10.1007/3-540-31662-0_6> and the other variants of hard and soft clustering algorithms. The cluster prototypes and membership matrices required by these partitioning algorithms are initialized with different initialization techniques that are available in the package inaparc'. As the distance metrics, not only the Euclidean distance but also a set of the commonly used distance metrics are available to use with some of the algorithms in the package.

An application to calculate a patient's pretest probability (PTP) for obstructive Coronary Artery Disease (CAD) from a collection of guidelines or studies. Guidelines usually comes from the American Heart Association (AHA), American College of Cardiology (ACC) or European Society of Cardiology (ESC). Examples of PTP scores that comes from studies are the 2020 Winther et al. basic, Risk Factor-weighted Clinical Likelihood (RF-CL) and Coronary Artery Calcium Score-weighted Clinical Likelihood (CACS-CL) models <doi:10.1016/j.jacc.2020.09.585>, 2019 Reeh et al. basic and clinical models <doi:10.1093/eurheartj/ehy806> and 2017 Fordyce et al. PROMISE Minimal-Risk Tool <doi:10.1001/jamacardio.2016.5501>. As diagnosis of CAD involves a costly and invasive coronary angiography procedure for patients, having a reliable PTP for CAD helps doctors to make better decisions during patient management. This ensures high risk patients can be diagnosed and treated early for CAD while avoiding unnecessary testing for low risk patients.

Producing the time-dependent receiver operating characteristic (ROC) curve through parametric approaches. Tools for generating random data, fitting, predicting and check goodness of fit are prepared. The methods are developed from the theoretical framework of proportional hazard model and copula functions. Using this package, users can now simulate parametric time-dependent ROC and run experiment to understand the behavior of the curve under different scenario.

This package implements the American Heart Association Predicting Risk of cardiovascular disease EVENTs (PREVENT) equations from Khan SS, Matsushita K, Sang Y, and colleagues (2023) <doi:10.1161/CIRCULATIONAHA.123.067626>, with optional comparison with their de facto predecessor, the Pooled Cohort Equations from the American Heart Association and American College of Cardiology (2013) <doi:10.1161/01.cir.0000437741.48606.98> and the revision to the Pooled Cohort Equations from Yadlowsky and colleagues (2018) <doi:10.7326/M17-3011>.

Psychometric mixture models based on flexmix infrastructure. At the moment Rasch mixture models with different parameterizations of the score distribution (saturated vs. mean/variance specification), Bradley-Terry mixture models, and MPT mixture models are implemented. These mixture models can be estimated with or without concomitant variables. See Frick et al. (2012) <doi:10.18637/jss.v048.i07> and Frick et al. (2015) <doi:10.1177/0013164414536183> for details on the Rasch mixture models.

Extract political party colors and logos from English Wikipedia party pages. Provides functions to scrape party infoboxes for color codes (HEX or HTML color names) and logo images. Includes integration with the Party Facts database for easy party lookups. Designed for political scientists and party researchers working with electoral and party data. For Party Facts, see Döring and Regel (2019) <doi:10.1177/1354068818820671> and Bederke, Döring, and Regel (2023) <doi:10.7910/DVN/TJINLQ>.

We provide inference for personalized medicine models. Namely, we answer the questions: (1) how much better does a purported personalized recommendation engine for treatments do over a business-as-usual approach and (2) is that difference statistically significant?

This package provides a simple package to grab a Bible proverb corresponding to the day of the month.

An implementation of the generalized power analysis for the local average treatment effect (LATE), proposed by Bansak (2020) <doi:10.1214/19-STS732>. Power analysis is in the context of estimating the LATE (also known as the complier average causal effect, or CACE), with calculations based on a test of the null hypothesis that the LATE equals 0 with a two-sided alternative. The method uses standardized effect sizes to place a conservative bound on the power under minimal assumptions. Package allows users to recover power, sample size requirements, or minimum detectable effect sizes. Package also allows users to work with absolute effects rather than effect sizes, to specify an additional assumption to narrow the bounds, and to incorporate covariate adjustment.

Bundles a number of established statistical methods to facilitate the visual interpretation of large datasets in sedimentary geology. Includes functionality for adaptive kernel density estimation, principal component analysis, correspondence analysis, multidimensional scaling, generalised procrustes analysis and individual differences scaling using a variety of dissimilarity measures. Univariate provenance proxies, such as single-grain ages or (isotopic) compositions are compared with the Kolmogorov-Smirnov, Kuiper, Wasserstein-2 or Sircombe-Hazelton L2 distances. Categorical provenance proxies such as chemical compositions are compared with the Aitchison and Bray-Curtis distances,and count data with the chi-square distance. Varietal data can either be converted to one or more distributional datasets, or directly compared using the multivariate Wasserstein distance. Also included are tools to plot compositional and count data on ternary diagrams and point-counting data on radial plots, to calculate the sample size required for specified levels of statistical precision, and to assess the effects of hydraulic sorting on detrital compositions. Includes an intuitive query-based user interface for users who are not proficient in R.

Estimating causal effects in the presence of post-treatment confounding using principal stratification. PStrata allows for customized monotonicity assumptions and exclusion restriction assumptions, with automatic full Bayesian inference supported by Stan'. The main workflow is PStrataModel() to specify the model, fit() to run MCMC sampling, estimate() to extract potential outcomes, and contrast() to compute causal effects. Visualization tools are provided for diagnosis and interpretation. See Liu and Li (2023) <doi:10.48550/arXiv.2304.02740> for details.

To calculate the raw, central and standardized moments from distribution parameters. To solve the distribution parameters based on user-provided mean, standard deviation, skewness and kurtosis. Normal, skew-normal, skew-t and Tukey g-&-h distributions are supported, for now.

This package implements donor-adjusted methods for forecasting conditional means and variances after structural shocks. Historical donor episodes are weighted using covariates observed before each shock, and their estimated post-shock effects are combined with forecasts from a target-series model. The methods build on Lin and Eck (2021) <doi:10.1016/j.ijforecast.2021.03.010>. The package supports donor balancing weights, structured donor pools, autoregressive integrated moving average models, and generalized autoregressive conditional heteroscedasticity models with external regressors.

This package provides functions for point process time series. Autocorrelation functions for spatial and temporal time series, and estimation of trend-plus-seasonality models for temporal and spatial time series. See Gervini (2025) <doi:10.1111/jtsa.70018> and Gervini and Kopischke (2026) <doi:10.48550/arXiv.2605.21884>.

This package creates a data frame with the residuals of partial regressions of the main explanatory variable and the variable of interest. This method follows the Frisch-Waugh-Lovell theorem, as explained in Lovell (2008) <doi:10.3200/JECE.39.1.88-91>.

This package provides a collection of miscellaneous functions for passive acoustics. Much of the content here is adapted to R from code written by other people. If you have any ideas of functions to add, please contact Taiki Sakai.