Within epidemic outbreaks, infections grow and decline differently between regions, and the velocity of spatial spread differs between countries. The swash library offers a set of model-based analyses for these topics. Spread velocity may be analysed with the Swash-Backwash Model for the Single Epidemic Wave and corresponding functions for bootstrap confidence intervals, country comparison, and visualization of results. Differences in epidemic growth between regions may be analysed using logistic growth models, exponential growth models, Hawkes processes and breakpoint analyses. All functionalities are accessed by the class "infpan" for infections panel data defined in this package, which is built from a data.frame provided by the user.

Terrestrial and marine predictors for species distribution modelling from multiple sources, including WorldClim <https://www.worldclim.org/>,, ENVIREM <https://envirem.github.io/>, Bio-ORACLE <https://bio-oracle.org/> and MARSPEC <http://www.marspec.org/>.

Implementations of the Single Transferable Vote counting system. By default, it uses the Cambridge method for surplus allocation and Droop method for quota calculation. Fractional surplus allocation and the Hare quota are available as options.

Facilitate phonetic transliteration between different languages. With support for both Hindi and English, this package provides a way to convert text between Hindi and English dataset. Whether you're working with multilingual data or need to convert dataset for analysis or presentation purposes, it offers a simple and efficient solution and harness the power of phonetic transliteration in your projects with this versatile package.

This package provides kernel weighting methods for estimation of proportional hazards models with intermittently observed longitudinal covariates. Cao H., Churpek M. M., Zeng D., and Fine J. P. (2015) <doi:10.1080/01621459.2014.957289>.

This package provides several datasets useful for processing and analysis of text in Turkish from an online shopping platform.

This package provides a network module-based generalized linear model for differential expression analysis with the count-based sequence data from RNA-Seq.

This package implements the Segment Profile Extraction via Pattern Analysis method for row-mean-centered multivariate data. Core capabilities include SVD-based row-isometric biplot construction, bias-corrected and accelerated, and percentile bootstrap confidence intervals for domain coordinates and per-person direction cosines, Procrustes alignment of bootstrap replicates across planes, parallel analysis for dimensionality selection, and segment profile reconstruction in planes defined by pairs of singular dimensions. A synthetic Woodcock-Johnson IV look-alike dataset is provided for examples and testing. The method is described in Kim and Grochowalski (2019) <doi:10.1007/s00357-018-9277-7>.

This package provides models to identify bimodally expressed genes from RNAseq data based on the Bimodality Index. SIBERG models the RNAseq data in the finite mixture modeling framework and incorporates mechanisms for dealing with RNAseq normalization. Three types of mixture models are implemented, namely, the mixture of log normal, negative binomial, or generalized Poisson distribution. See Tong et al. (2013) <doi:10.1093/bioinformatics/bts713>.

This package implements the basic elements of the multi-model inference paradigm for up to twenty species-area relationship models (SAR), using simple R list-objects and functions, as in Triantis et al. 2012 <DOI:10.1111/j.1365-2699.2011.02652.x>. The package is scalable and users can easily create their own model and data objects. Additional SAR related functions are provided.

Implementation of the shuffle estimator, a non-parametric estimator for signal and noise variance under mild noise correlations.

Parameter inference methods for models defined implicitly using a random simulator. Inference is carried out using simulation-based estimates of the log-likelihood of the data. The inference methods implemented in this package are explained in Park, J. (2025) <doi:10.48550/arxiv.2311.09446>. These methods are built on a simulation metamodel which assumes that the estimates of the log-likelihood are approximately normally distributed with the mean function that is locally quadratic around its maximum. Parameter estimation and uncertainty quantification can be carried out using the ht() function (for hypothesis testing) and the ci() function (for constructing a confidence interval for one-dimensional parameters).

Finds causal connections in precision data, finds lags and embeddings in time series, guides training of neural networks and other smooth models, evaluates their performance, gives a mathematically grounded answer to the over-training problem. Smooth regression is based on the Gamma test, which measures smoothness in a multivariate relationship. Causal relations are smooth, noise is not. sr includes the Gamma test and search techniques that use it. References: Evans & Jones (2002) <doi:10.1098/rspa.2002.1010>, AJ Jones (2004) <doi:10.1007/s10287-003-0006-1>.

SMART trial design, as described by He, J., McClish, D., Sabo, R. (2021) <doi:10.1080/19466315.2021.1883472>, includes multiple stages of randomization, where participants are randomized to an initial treatment in the first stage and then subsequently re-randomized between treatments in the following stage.

An implementation of semi-supervised regression methods including self-learning and co-training by committee based on Hady, M. F. A., Schwenker, F., & Palm, G. (2009) <doi:10.1007/978-3-642-04274-4_13>. Users can define which set of regressors to use as base models from the caret package, other packages, or custom functions.

This package provides a tool for producing synthetic versions of microdata containing confidential information so that they are safe to be released to users for exploratory analysis. The key objective of generating synthetic data is to replace sensitive original values with synthetic ones causing minimal distortion of the statistical information contained in the data set. Variables, which can be categorical or continuous, are synthesised one-by-one using sequential modelling. Replacements are generated by drawing from conditional distributions fitted to the original data using parametric or classification and regression trees models. Data are synthesised via the function syn() which can be largely automated, if default settings are used, or with methods defined by the user. Optional parameters can be used to influence the disclosure risk and the analytical quality of the synthesised data. For a description of the implemented method see Nowok, Raab and Dibben (2016) <doi:10.18637/jss.v074.i11>. Functions to assess identity and attribute disclosure for the original and for the synthetic data are included in the package, and their use is illustrated in a vignette on disclosure (Practical Privacy Metrics for Synthetic Data).

An interface to explore trends in Twitter data using the Storywrangler Application Programming Interface (API), which can be found here: <https://github.com/janeadams/storywrangler>.

Fast computation of multivariate analyses of small (10s to 100s markers) to big (1000s to 100000s) genotype data. Runs Principal Component Analysis allowing for centering, z-score standardization and scaling for genetic drift, projection of ancient samples to modern genetic space and multivariate tests for differences in group location (Permutation-Based Multivariate Analysis of Variance) and dispersion (Permutation-Based Multivariate Analysis of Dispersion).

Decode raw SYNOP (surface synoptic observations) messages into data frames, extracting data from Sections 0, 1, and 3, including temperature, dew point, pressure, wind, clouds, and precipitation. Available functions to download SYNOP messages from Ogimet <https://www.ogimet.com/> if needed. The decoding logic follows the specifications defined in the World Meteorological Organization (2019) "Manual on Codes, Volume I.1 (WMO-No. 306)".

Variable and interaction selection are essential to classification in high-dimensional setting. In this package, we provide the implementation of SODA procedure, which is a forward-backward algorithm that selects both main and interaction effects under logistic regression and quadratic discriminant analysis. We also provide an extension, S-SODA, for dealing with the variable selection problem for semi-parametric models with continuous responses.

This package provides a set of functions is provided for 1) the stratum lengths analysis along a chosen direction, 2) fast estimation of continuous lag spatial Markov chains model parameters and probability computing (also for large data sets), 3) transition probability maps and transiograms drawing, 4) simulation methods for categorical random fields. More details on the methodology are discussed in Sartore (2013) <doi:10.32614/RJ-2013-022> and Sartore et al. (2016) <doi:10.1016/j.cageo.2016.06.001>.

This package implements variable selection procedures for low to moderate size generalized linear regressions models. It includes the STOPES functions for linear regression (Capanu M, Giurcanu M, Begg C, Gonen M, Optimized variable selection via repeated data splitting, Statistics in Medicine, 2020, 19(6):2167-2184) as well as subsampling based optimization methods for generalized linear regression models (Marinela Capanu, Mihai Giurcanu, Colin B Begg, Mithat Gonen, Subsampling based variable selection for generalized linear models).

Using any importation code designed for SAS users to read ASCII files into sas7bdat files, this package parses through the INPUT block of a .sas syntax file to design the parameters needed for a read.fwf() function call. This allows the user to specify the location of the ASCII (often a .dat') file and the location of the SAS syntax file, and then load the data frame directly into R in just one step.

This package provides significance controlled variable selection algorithms with different directions (forward, backward, stepwise) based on diverse criteria (AIC, BIC, adjusted r-square, PRESS, or p-value). The algorithm selects a final model with only significant variables defined as those with significant p-values after multiple testing correction such as Bonferroni, False Discovery Rate, etc. See Zambom and Kim (2018) <doi:10.1002/sta4.210>.