This contains functions and data used by the Open Visualization Academy classes on data processing and visualization. The tutorial included with this package requires the gradethis package which can be installed using "remotes::install_github('rstudio/gradethis')".

Generate 2, 3 or 4-dimensional gradient noise. The noise function is comparable to classic Perlin noise, but with less directional artefacts and lower computational overhead. It can have applications in procedural generation or (flow fields) simulations.

This package provides a collection of functions to construct sets of orthogonal polynomials and their recurrence relations. Additional functions are provided to calculate the derivative, integral, value and roots of lists of polynomial objects.

An interface to the search API of HAL <https://hal.science/>, the French open archive for scholarly documents from all academic fields. This package provides programmatic access to the API <https://api.archives-ouvertes.fr/docs> and allows to search for records and download documents.

Estimates win ratio or Mann-Whitney parameter for two group comparisons using ordered composite endpoints with right censoring as described in Follmann, Fay, Hamasaki, and Evans (2020)<doi:10.1002/sim.7890>.

Outlier detection method that flags suspicious values within observations, constrasting them against the normal values in a user-readable format, potentially describing conditions within the data that make a given outlier more rare. Full procedure is described in Cortes (2020) <doi:10.48550/arXiv.2001.00636>. Loosely based on the GritBot <https://www.rulequest.com/gritbot-info.html> software.

An R autograding extension for Otter-Grader (<https://otter-grader.readthedocs.io>). It supports grading R scripts, R Markdown documents, and R Jupyter Notebooks.

An approach to outlier detection in RNA-seq and related data based on five statistics. OutSeekR implements an outlier test by comparing the distributions of these statistics in observed data with those of simulated null data.

Sample from the limiting distributions of empirical Wasserstein distances under the null hypothesis and under the alternative. Perform a two-sample test on multivariate data using these limiting distributions and binning.

This package provides a lightweight, fully vectorized N-body physics engine built for the R ecosystem. Simulate and visualize complex orbital mechanics, celestial trajectories, and gravitational interactions using tidy data principles. Features multiple numerical integration methods, including the energy-conserving velocity Verlet algorithm (Verlet (1967) <doi:10.1103/PhysRev.159.98>), to ensure highly stable orbital propagation. Gravitational N-body methods follow Aarseth (2003, ISBN:0-521-43272-3).

Optimal k Nearest Neighbours Ensemble is an ensemble of base k nearest neighbour models each constructed on a bootstrap sample with a random subset of features. k closest observations are identified for a test point "x" (say), in each base k nearest neighbour model to fit a stepwise regression to predict the output value of "x". The final predicted value of "x" is the mean of estimates given by all the models. The implemented model takes training and test datasets and trains the model on training data to predict the test data. Ali, A., Hamraz, M., Kumam, P., Khan, D.M., Khalil, U., Sulaiman, M. and Khan, Z. (2020) <DOI:10.1109/ACCESS.2020.3010099>.

O-statistics, or overlap statistics, measure the degree of community-level trait overlap. They are estimated by fitting nonparametric kernel density functions to each speciesâ trait distribution and calculating their areas of overlap. For instance, the median pairwise overlap for a community is calculated by first determining the overlap of each species pair in trait space, and then taking the median overlap of each species pair in a community. This median overlap value is called the O-statistic (O for overlap). The Ostats() function calculates separate univariate overlap statistics for each trait, while the Ostats_multivariate() function calculates a single multivariate overlap statistic for all traits. O-statistics can be evaluated against null models to obtain standardized effect sizes. Ostats is part of the collaborative Macrosystems Biodiversity Project "Local- to continental-scale drivers of biodiversity across the National Ecological Observatory Network (NEON)." For more information on this project, see the Macrosystems Biodiversity Website (<https://neon-biodiversity.github.io/>). Calculation of O-statistics is described in Read et al. (2018) <doi:10.1111/ecog.03641>, and a teaching module for introducing the underlying biological concepts at an undergraduate level is described in Grady et al. (2018) <http://tiee.esa.org/vol/v14/issues/figure_sets/grady/abstract.html>.

Implementation of a likelihood ratio test of differential onset of senescence between two groups. Given two groups with measures of age and of an individual trait likely to be subjected to senescence (e.g. body mass), OnAge provides an asymptotic p-value for the null hypothesis that senescence starts at the same age in both groups. The package implements the procedure used in Douhard et al. (2017) <doi:10.1111/oik.04421>.

Utilize an orthogonality constrained optimization algorithm of Wen & Yin (2013) <DOI:10.1007/s10107-012-0584-1> to solve a variety of dimension reduction problems in the semiparametric framework, such as Ma & Zhu (2012) <DOI:10.1080/01621459.2011.646925>, Ma & Zhu (2013) <DOI:10.1214/12-AOS1072>, Sun, Zhu, Wang & Zeng (2019) <DOI:10.1093/biomet/asy064> and Zhou, Zhu & Zeng (2021) <DOI:10.1093/biomet/asaa087>. The package also implements some existing dimension reduction methods such as hMave by Xia, Zhang, & Xu (2010) <DOI:10.1198/jasa.2009.tm09372> and partial SAVE by Feng, Wen & Zhu (2013) <DOI:10.1080/01621459.2012.746065>. It also serves as a general purpose optimization solver for problems with orthogonality constraints, i.e., in Stiefel manifold. Parallel computing for approximating the gradient is enabled through OpenMP'.

This package implements the Univariate Bootstrap and the Traditional (Naive) Bootstrap for resampling multivariate data while preserving covariance structure. Also provides functions for DeFries-Fulker behavioral genetics models, including the Rodgers-Kohler formulation with robust standard errors.

Represents the basis functions for B-splines in a simple matrix formulation that facilitates, taking integrals, derivatives, and making orthogonal the basis functions.

This package provides simple crosstab output with optional statistics (e.g., Goodman-Kruskal Gamma, Somers d, and Kendall's tau-b) as well as two-way and one-way tables. The package is used within the statistics component of the Masters of Science (MSc) in Social Science of the Internet at the Oxford Internet Institute (OII), University of Oxford, but the functions should be useful for general data analysis and especially for analysis of categorical and ordinal data.

Identifies an optimal transformation of a surrogate marker such that the proportion of treatment effect explained can be inferred based on the transformation of the surrogate and nonparametrically estimates two model-free quantities of this proportion. Details are described in Wang et al (2020) <doi:10.1093/biomet/asz065>.

This package provides implementations of some of the most important outlier detection algorithms. Includes a tutorial mode option that shows a description of each algorithm and provides a step-by-step execution explanation of how it identifies outliers from the given data with the specified input parameters. References include the works of Azzedine Boukerche, Lining Zheng, and Omar Alfandi (2020) <doi:10.1145/3381028>, Abir Smiti (2020) <doi:10.1016/j.cosrev.2020.100306>, and Xiaogang Su, Chih-Ling Tsai (2011) <doi:10.1002/widm.19>.

Computes the pdf, cdf, quantile function, hazard function and generating random numbers for Odd log-logistic family (OLL-G). This family have been developed by different authors in the recent years. See Alizadeh (2019) <doi:10.31801/cfsuasmas.542988> for example.

Quantifies hypothesis to data fit for repeated measures and longitudinal data, as described by Thorngate (1987) <doi:10.1016/S0166-4115(08)60083-7> and Grice et al., (2015) <doi:10.1177/2158244015604192>. Hypothesis and data are encoded as pairwise relative orderings which are then compared to determine the percentage of orderings in the data that are matched by the hypothesis.

Generates n hierarchical clustering hypotheses on subsets of classifiers (usually species in community ecology studies). The n clustering hypotheses are combined to generate a generalized cluster, and computes three metrics of support. 1) The average proportion of elements conforming the group in each of the n clusters (integrity). And 2) the contamination, i.e., the average proportion of elements from other groups that enter a focal group. 3) The probability of existence of the group gives the integrity and contamination in a Bayesian approach.

This tool was designed to assess the sensitivity of research findings to omitted variables when estimating causal effects using propensity score (PS) weighting. This tool produces graphics and summary results that will enable a researcher to quantify the impact an omitted variable would have on their results. Burgette et al. (2021) describe the methodology behind the primary function in this package, ov_sim. The method is demonstrated in Griffin et al. (2020) <doi:10.1016/j.jsat.2020.108075>.

Estimate the positron emission tomography (PET) neuroreceptor occupancies from the total volumes of distribution of a set of regions of interest. Fitting methods include the simple reference region', ordinary least squares (sometimes known as occupancy plot), and restricted maximum likelihood estimation'.