Data sets used in the book "R Graphics Cookbook" by Winston Chang, published by O'Reilly Media.

We provide an efficient implementation for two-step multi-source transfer learning algorithms in high-dimensional generalized linear models (GLMs). The elastic-net penalized GLM with three popular families, including linear, logistic and Poisson regression models, can be fitted. To avoid negative transfer, a transferable source detection algorithm is proposed. We also provides visualization for the transferable source detection results. The details of methods can be found in "Tian, Y., & Feng, Y. (2023). Transfer learning under high-dimensional generalized linear models. Journal of the American Statistical Association, 118(544), 2684-2697.".

This package provides a general, flexible framework for estimating parameters and empirical sandwich variance estimator from a set of unbiased estimating equations (i.e., M-estimation in the vein of Stefanski & Boos (2002) <doi:10.1198/000313002753631330>). All examples from Stefanski & Boos (2002) are published in the corresponding Journal of Statistical Software paper "The Calculus of M-Estimation in R with geex" by Saul & Hudgens (2020) <doi:10.18637/jss.v092.i02>. Also provides an API to compute finite-sample variance corrections.

This package provides tools for semantic segmentation of geospatial data using convolutional neural network-based deep learning. Utility functions allow for creating masks, image chips, data frames listing image chips in a directory, and DataSets for use within DataLoaders. Additional functions are provided to serve as checks during the data preparation and training process. A UNet architecture can be defined with 4 blocks in the encoder, a bottleneck block, and 4 blocks in the decoder. The UNet can accept a variable number of input channels, and the user can define the number of feature maps produced in each encoder and decoder block and the bottleneck. Users can also choose to (1) replace all rectified linear unit (ReLU) activation functions with leaky ReLU or swish, (2) implement attention gates along the skip connections, (3) implement squeeze and excitation modules within the encoder blocks, (4) add residual connections within all blocks, (5) replace the bottleneck with a modified atrous spatial pyramid pooling (ASPP) module, and/or (6) implement deep supervision using predictions generated at each stage in the decoder. A unified focal loss framework is implemented after Yeung et al. (2022) <doi:10.1016/j.compmedimag.2021.102026>. We have also implemented assessment metrics using the luz package including F1-score, recall, and precision. Trained models can be used to predict to spatial data without the need to generate chips from larger spatial extents. Functions are available for performing accuracy assessment. The package relies on torch for implementing deep learning, which does not require the installation of a Python environment. Raster geospatial data are handled with terra'. Models can be trained using a Compute Unified Device Architecture (CUDA)-enabled graphics processing unit (GPU); however, multi-GPU training is not supported by torch in R'.

Projections are common dimensionality reduction methods, which represent high-dimensional data in a two-dimensional space. However, when restricting the output space to two dimensions, which results in a two dimensional scatter plot (projection) of the data, low dimensional similarities do not represent high dimensional distances coercively [Thrun, 2018] <DOI: 10.1007/978-3-658-20540-9>. This could lead to a misleading interpretation of the underlying structures [Thrun, 2018]. By means of the 3D topographic map the generalized Umatrix is able to depict errors of these two-dimensional scatter plots. The package is derived from the book of Thrun, M.C.: "Projection Based Clustering through Self-Organization and Swarm Intelligence" (2018) <DOI:10.1007/978-3-658-20540-9> and the main algorithm called simplified self-organizing map for dimensionality reduction methods is published in <DOI: 10.1016/j.mex.2020.101093>.

Implementation of functions, which combines binomial calculation and data visualisation, to analyse the differences in publishing authorship by gender described in Day et al. (2020) <doi:10.1039/C9SC04090K>. It should only be used when self-reported gender is unavailable.

The gamma-Orthogonal Matching Pursuit (gamma-OMP) is a recently suggested modification of the OMP feature selection algorithm for a wide range of response variables. The package offers many alternative regression models, such linear, robust, survival, multivariate etc., including k-fold cross-validation. References: Tsagris M., Papadovasilakis Z., Lakiotaki K. and Tsamardinos I. (2018). "Efficient feature selection on gene expression data: Which algorithm to use?" BioRxiv. <doi:10.1101/431734>. Tsagris M., Papadovasilakis Z., Lakiotaki K. and Tsamardinos I. (2022). "The gamma-OMP algorithm for feature selection with application to gene expression data". IEEE/ACM Transactions on Computational Biology and Bioinformatics 19(2): 1214--1224. <doi:10.1109/TCBB.2020.3029952>.

This package performs test procedures for general hypothesis testing problems for four multivariate coefficients of variation (Ditzhaus and Smaga, 2023 <arXiv:2301.12009>). We can verify the global hypothesis about equality as well as the particular hypotheses defined by contrasts, e.g., we can conduct post hoc tests. We also provide the simultaneous confidence intervals for contrasts.

This package implements a method of iteratively collapsing the rows of a contingency table, two at a time, by selecting the pair of categories whose combination yields a new table with the smallest loss of chi-squared, as described by Greenacre, M.J. (1988) <doi:10.1007/BF01901670>. The result is compatible with the class of object returned by the stats package's hclust() function and can be used similarly (plotted as a dendrogram, cut, etc.). Additional functions are provided for automatic cutting and diagnostic plotting.

Estimation of the variogram through trimmed mean, radial basis functions (optimization, prediction and cross-validation), summary statistics from cross-validation, pocket plot, and design of optimal sampling networks through sequential and simultaneous points methods.

This package provides a ggplot2'-consistent approach to generating 2D displays of volumetric brain imaging data. Display data from multiple NIfTI images using standard ggplot2 conventions such scales, limits, and themes to control the appearance of displays. The resulting plots are returned as patchwork objects, inheriting from ggplot', allowing for any standard modifications of display aesthetics supported by ggplot2'.

This package provides a collection of custom ggplot2'-based visualizations for data exploration and analysis. Each function handles data preprocessing and returns a object that can be further customized using standard ggplot2 syntax.

Comparing two independent or paired groups across a range of descriptive statistics, enabling the evaluation of potential differences in central tendency (mean, median), dispersion (variance, interquartile range), shape (skewness, kurtosis), and distributional characteristics (various quantiles). The analytical framework incorporates parametric t-tests, non-parametric Wilcoxon tests, permutation tests, and bootstrap resampling techniques to assess the statistical significance of observed differences.

Realize three approaches for Gene-Environment interaction analysis. All of them adopt Sparse Group Minimax Concave Penalty to identify important G variables and G-E interactions, and simultaneously respect the hierarchy between main G and G-E interaction effects. All the three approaches are available for Linear, Logistic, and Poisson regression. Also realize to mine and construct prior information for G variables and G-E interactions.

Interact with the Google Cloud Vision <https://cloud.google.com/vision/> API in R. Part of the cloudyr <https://cloudyr.github.io/> project.

This package provides routines to estimate the Mixture Transition Distribution Model based on Raftery (1985) <http://www.jstor.org/stable/2345788> and Nicolau (2014) <doi:10.1111/sjos.12087> specifications, for multivariate data. Additionally, provides a function for the estimation of a new model for multivariate non-homogeneous Markov chains. This new specification, Generalized Multivariate Markov Chains (GMMC) was proposed by Carolina Vasconcelos and Bruno Damasio and considers (continuous or discrete) covariates exogenous to the Markov chain.

This package performs genetic algorithm (Scrucca, L (2013) <doi:10.18637/jss.v053.i04>) assisted genomic best liner unbiased prediction for genomic selection. It also provides a binning method in natural population for genomic selection under the principle of linkage disequilibrium for dimensional reduction.

An interface for fitting generalized additive models (GAMs) and generalized additive mixed models (GAMMs) using the lme4 package as the computational engine, as described in Helwig (2024) <doi:10.3390/stats7010003>. Supports default and formula methods for model specification, additive and tensor product splines for capturing nonlinear effects, and automatic determination of spline type based on the class of each predictor. Includes an S3 plot method for visualizing the (nonlinear) model terms, an S3 predict method for forming predictions from a fit model, and an S3 summary method for conducting significance testing using the Bayesian interpretation of a smoothing spline.

Routines for log-linear models of incomplete contingency tables, including some latent class models, via EM and Fisher scoring approaches. Allows bootstrapping. See Espeland and Hui (1987) <doi:10.2307/2531553> for general approach.

Two arms clinical trials required sample size is calculated in the comprehensive parametric context. The calculation is based on the type of endpoints(continuous/binary/time-to-event/ordinal), design (parallel/crossover), hypothesis tests (equality/noninferiority/superiority/equivalence), trial arms noncompliance rates and expected loss of follow-up. Methods are described in: Chow SC, Shao J, Wang H, Lokhnygina Y (2017) <doi:10.1201/9781315183084>, Wittes, J (2002) <doi:10.1093/epirev/24.1.39>, Sato, T (2000) <doi:10.1002/1097-0258(20001015)19:19%3C2689::aid-sim555%3E3.0.co;2-0>, Lachin J M, Foulkes, M A (1986) <doi:10.2307/2531201>, Whitehead J(1993) <doi:10.1002/sim.4780122404>, Julious SA (2023) <doi:10.1201/9780429503658>.

Circular genomic permutation approach uses genome wide association studies (GWAS) results to establish the significance of pathway/gene-set associations whilst accounting for genomic structure. All single nucleotide polymorphisms (SNPs) in the GWAS are placed in a circular genome according to their location. Then the complete set of SNP association p-values are permuted by rotation with respect to the SNPs genomic locations. Two testing frameworks are available: permutations at the gene level, and permutations at the SNP level. The permutation at the gene level uses Fisher's combination test to calculate a single gene p-value, followed by the hypergeometric test. The SNP count methodology maps each SNP to pathways/gene-sets and calculates the proportion of SNPs for the real and the permutated datasets above a pre-defined threshold. Genomicper requires a matrix of GWAS association p-values and SNPs annotation to genes. Pathways can be obtained from within the package or can be provided by the user. Cabrera et al (2012) <doi:10.1534/g3.112.002618> .

This package provides a system for fitting Gompertz Curve in a Time Series Data.

Function gmcmtx0() computes a more reliable (general) correlation matrix. Since causal paths from data are important for all sciences, the package provides many sophisticated functions. causeSummBlk() and causeSum2Blk() give easy-to-interpret causal paths. Let Z denote control variables and compare two flipped kernel regressions: X=f(Y, Z)+e1 and Y=g(X, Z)+e2. Our criterion Cr1 says that if |e1*Y|>|e2*X| then variation in X is more "exogenous or independent" than in Y, and the causal path is X to Y. Criterion Cr2 requires |e2|<|e1|. These inequalities between many absolute values are quantified by four orders of stochastic dominance. Our third criterion Cr3, for the causal path X to Y, requires new generalized partial correlations to satisfy |r*(x|y,z)|< |r*(y|x,z)|. The function parcorVec() reports generalized partials between the first variable and all others. The package provides several R functions including get0outliers() for outlier detection, bigfp() for numerical integration by the trapezoidal rule, stochdom2() for stochastic dominance, pillar3D() for 3D charts, canonRho() for generalized canonical correlations, depMeas() measures nonlinear dependence, and causeSummary(mtx) reports summary of causal paths among matrix columns. Portfolio selection: decileVote(), momentVote(), dif4mtx(), exactSdMtx() can rank several stocks. Functions whose names begin with boot provide bootstrap statistical inference, including a new bootGcRsq() test for "Granger-causality" allowing nonlinear relations. A new tool for evaluation of out-of-sample portfolio performance is outOFsamp(). Panel data implementation is now included. See eight vignettes of the package for theory, examples, and usage tips. See Vinod (2019) \doi10.1080/03610918.2015.1122048.

Spatio-temporal radial basis functions (optimization, prediction and cross-validation), summary statistics from cross-validation, Adjusting distance-based linear regression model and generation of the principal coordinates of a new individual from Gower's distance.