Set of shiny'-based RStudio add-ins for interactively creating datasets through graphical interfaces. Users can adjust graphical elements to define data generation parameters, and the resulting datasets can be saved to temporary RDS files for further analysis or visualization. Methods are described in: Chang et al. (2024) <https://CRAN.R-project.org/package=shiny>; Bostock et al. (2011) <doi:10.1109/TVCG.2011.185>.

Implementation of some Deep Learning methods. Includes multilayer perceptron, different activation functions, regularisation strategies, stochastic gradient descent and dropout. Thanks go to the following references for helping to inspire and develop the package: Ian Goodfellow, Yoshua Bengio, Aaron Courville, Francis Bach (2016, ISBN:978-0262035613) Deep Learning. Terrence J. Sejnowski (2018, ISBN:978-0262038034) The Deep Learning Revolution. Grant Sanderson (3brown1blue) <https://www.youtube.com/playlist?list=PLZHQObOWTQDNU6R1_67000Dx_ZCJB-3pi> Neural Networks YouTube playlist. Michael A. Nielsen <http://neuralnetworksanddeeplearning.com/> Neural Networks and Deep Learning.

Fast functions for effective sample size, weighted multivariate mean, variance, and quantile computation, and weight diagnostic plot for generic importance sampling type or other probability weighted samples.

Dynamic CUR (dCUR) boosts the CUR decomposition (Mahoney MW., Drineas P. (2009) <doi:10.1073/pnas.0803205106>) varying the k, the number of columns and rows used, and its final purposes to help find the stage, which minimizes the relative error to reduce matrix dimension. The goal of CUR Decomposition is to give a better interpretation of the matrix decomposition employing proper variable selection in the data matrix, in a way that yields a simplified structure. Its origins come from analysis in genetics. The goal of this package is to show an alternative to variable selection (columns) or individuals (rows). The idea proposed consists of adjusting the probability distributions to the leverage scores and selecting the best columns and rows that minimize the reconstruction error of the matrix approximation ||A-CUR||. It also includes a method that recalibrates the relative importance of the leverage scores according to an external variable of the user's interest.

This package provides an implementation of a mixture of hidden Markov models (HMMs) for discrete sequence data in the Discrete Bayesian HMM Clustering (DBHC) algorithm. The DBHC algorithm is an HMM Clustering algorithm that finds a mixture of discrete-output HMMs while using heuristics based on Bayesian Information Criterion (BIC) to search for the optimal number of HMM states and the optimal number of clusters.

Statistical modelling and forecasting in claims reserving in non-life insurance under the Double Chain Ladder framework by Martinez-Miranda, Nielsen and Verrall (2012).

Alpha and beta diversity for taxonomic (TD), functional (FD), and phylogenetic (PD) dimensions based on rasters. Spatial and temporal beta diversity can be partitioned into replacement and richness difference components. It also calculates standardized effect size for FD and PD alpha diversity and the average individual traits across multilayer rasters. The layers of the raster represent species, while the cells represent communities. Methods details can be found at Cardoso et al. 2022 <https://CRAN.R-project.org/package=BAT> and Heming et al. 2023 <https://CRAN.R-project.org/package=SESraster>.

This package provides a set of functions to quantify the relationship between development rate and temperature and to build phenological models. The package comprises a set of models and estimated parameters borrowed from a literature review in ectotherms. The methods and literature review are described in Rebaudo et al. (2018) <doi:10.1111/2041-210X.12935>, Rebaudo and Rabhi (2018) <doi:10.1111/eea.12693>, and Regnier et al. (2021) <doi:10.1093/ee/nvab115>. An example can be found in Rebaudo et al. (2017) <doi:10.1007/s13355-017-0480-5>.

This package provides a simple way of fitting detection functions to distance sampling data for both line and point transects. Adjustment term selection, left and right truncation as well as monotonicity constraints and binning are supported. Abundance and density estimates can also be calculated (via a Horvitz-Thompson-like estimator) if survey area information is provided. See Miller et al. (2019) <doi:10.18637/jss.v089.i01> for more information on methods and <https://distancesampling.org/resources/vignettes.html> for example analyses.

This package provides a big-data-friendly and memory-efficient difference-in-differences estimator for staggered (and non-staggered) treatment contexts.

This package implements two out-of box classifiers presented in <doi:10.1002/env.2848> for distinguishing forest and non-forest terrain images. Under these algorithms, there are frequentist approaches: one parametric, using stable distributions, and another one- non-parametric, using the squared Mahalanobis distance. The package also contains functions for data handling and building of new classifiers as well as some test data set.

Efficient Global Optimization (EGO) algorithm as described in "Roustant et al. (2012)" <doi:10.18637/jss.v051.i01> and adaptations for problems with noise ("Picheny and Ginsbourger, 2012") <doi:10.1016/j.csda.2013.03.018>, parallel infill, and problems with constraints.

Generally, most of the packages specify the probability density function, cumulative distribution function, quantile function, and random numbers generation of the probability distributions. The present package allows to compute some important distributional properties, including the first four ordinary and central moments, Pearson's coefficient of skewness and kurtosis, the mean and variance, coefficient of variation, median, and quartile deviation at some parametric values of several well-known and extensively used probability distributions.

It is sometimes necessary to create documentation for all files in a directory. Doing so by hand can be very tedious. This task is made fast and reproducible using the functionality of documenter'. It aggregates all text files in a directory and its subdirectories into a single word document in a semi-automated fashion.

Measure of agreement delta was originally by Martà n & Femia (2004) <DOI:10.1348/000711004849268>. Since then has been considered as agreement measure for different fields, since their behavior is usually better than the usual kappa index by Cohen (1960) <DOI:10.1177/001316446002000104>. The main issue with delta is that can not be computed by hand contrary to kappa. The current algorithm is based on the Version 5 of the delta windows program that can be found on <https://www.ugr.es/~bioest/software/delta/cmd.php?seccion=downloads>.

This package provides functions to compute coefficients measuring the dependence of two or more than two variables. The functions can be deployed to gain information about functional dependencies of the variables with emphasis on monotone functions. The statistics describe how well one response variable can be approximated by a monotone function of other variables. In regression analysis the variable selection is an important issue. In this framework the functions could be useful tools in modeling the regression function. Detailed explanations on the subject can be found in papers Liebscher (2014) <doi:10.2478/demo-2014-0004>; Liebscher (2017) <doi:10.1515/demo-2017-0012>; Liebscher (2021): <https://arfjournals.com/image/catalog/Journals%20Papers/AJSS/No%202%20(2021)/4-AJSS_123-150.pdf>; Liebscher (2021): Kendall regression coefficient. Computational Statistics and Data Analysis 157. 107140.

Simple functions to deflate nominal Brazilian Reais using several popular price indexes downloaded from the Brazilian Institute for Applied Economic Research.

The FBED and mmpc variable selection algorithms have been implemented using the distance correlation. The references include: Tsamardinos I., Aliferis C. F. and Statnikov A. (2003). "Time and sample efficient discovery of Markovblankets and direct causal relations". In Proceedings of the ninth ACM SIGKDD international Conference. <doi:10.1145/956750.956838>. Borboudakis G. and Tsamardinos I. (2019). "Forward-backward selection with early dropping". Journal of Machine Learning Research, 20(8): 1--39. <doi:10.48550/arXiv.1705.10770>. Huo X. and Szekely G.J. (2016). "Fast computing for distance covariance". Technometrics, 58(4): 435--447. <doi:10.1080/00401706.2015.1054435>.

Data screening is an important first step of any statistical analysis. dataReporter auto generates a customizable data report with a thorough summary of the checks and the results that a human can use to identify possible errors. It provides an extendable suite of test for common potential errors in a dataset. See Petersen AH, Ekstrøm CT (2019). "dataMaid: Your Assistant for Documenting Supervised Data Quality Screening in R." _Journal of Statistical Software_, *90*(6), 1-38 <doi:10.18637/jss.v090.i06> for more information.

S4 classes around infrastructure provided by the coda and dclone packages to make package development easy as a breeze with data cloning for hierarchical models.

Develop and evaluate treatment rules based on: (1) the standard indirect approach of split-regression, which fits regressions separately in both treatment groups and assigns an individual to the treatment option under which predicted outcome is more desirable; (2) the direct approach of outcome-weighted-learning proposed by Yingqi Zhao, Donglin Zeng, A. John Rush, and Michael Kosorok (2012) <doi:10.1080/01621459.2012.695674>; (3) the direct approach, which we refer to as direct-interactions, proposed by Shuai Chen, Lu Tian, Tianxi Cai, and Menggang Yu (2017) <doi:10.1111/biom.12676>. Please see the vignette for a walk-through of how to start with an observational dataset whose design is understood scientifically and end up with a treatment rule that is trustworthy statistically, along with an estimation of rule benefit in an independent sample.

Statistical methods for DNA mixture analysis. This package is a lite-version of the DNAmixtures package to allow users without a HUGIN software license to experiment with the statistical methodology. While the lite-version aims to provide the full functionality it is noticeably less efficient than the original DNAmixtures package. For details on implementation and methodology see <https://dnamixtures.r-forge.r-project.org/>.

An interface to DifferentialEquations.jl <https://diffeq.sciml.ai/dev/> from the R programming language. It has unique high performance methods for solving ordinary differential equations (ODE), stochastic differential equations (SDE), delay differential equations (DDE), differential-algebraic equations (DAE), and more. Much of the functionality, including features like adaptive time stepping in SDEs, are unique and allow for multiple orders of magnitude speedup over more common methods. Supports GPUs, with support for CUDA (NVIDIA), AMD GPUs, Intel oneAPI GPUs, and Apple's Metal (M-series chip GPUs). diffeqr attaches an R interface onto the package, allowing seamless use of this tooling by R users. For more information, see Rackauckas and Nie (2017) <doi:10.5334/jors.151>.

Differential exon usage test for RNA-Seq data via an empirical Bayes shrinkage method for the dispersion parameter the utilizes inclusion-exclusion data to analyze the propensity to skip an exon across groups. The input data consists of two matrices where each row represents an exon and the columns represent the biological samples. The first matrix is the count of the number of reads expressing the exon for each sample. The second matrix is the count of the number of reads that either express the exon or explicitly skip the exon across the samples, a.k.a. the total count matrix. Dividing the two matrices yields proportions representing the propensity to express the exon versus skipping the exon for each sample.