Knowledge space theory by Doignon and Falmagne (1999) <doi:10.1007/978-3-642-58625-5> is a set- and order-theoretical framework which proposes mathematical formalisms to operationalize knowledge structures in a particular domain. The kstIO package provides basic functionalities to read and write KST data from/to files to be used together with the kst', kstMatrix', CDSS', pks', or DAKS packages.

Tests the homogeneity of intraclass kappa statistics obtained from independent studies or a stratified study with binary results. It is desired to compare the kappa statistics obtained in multi-center studies or in a single stratified study to give a common or summary kappa using all available information. If the homogeneity test of these kappa statistics is not rejected, then it is possible to make inferences over a single kappa statistic that summarizes all the studies. Muammer Albayrak, Kemal Turhan, Yasemin Yavuz, Zeliha Aydin Kasap (2019) <doi:10.1080/03610918.2018.1538457> Jun-mo Nam (2003) <doi:10.1111/j.0006-341X.2003.00118.x> Jun-mo Nam (2005) <doi:10.1002/sim.2321>Mousumi Banerjee, Michelle Capozzoli, Laura McSweeney,Debajyoti Sinha (1999) <doi:10.2307/3315487> Allan Donner, Michael Eliasziw, Neil Klar (1996) <doi:10.2307/2533154>.

Computes group centrality scores and identifies the most central group of players in a network.

This package provides the function to calculate the kernel-lasso expansion, Z-score, and max-min-scale standardization.It can increase the dimension of existed dataset and remove abundant features by lasso. Z Dai, L Jiayi, T Gong, C Wang (2021) <doi:10.1088/1742-6596/1955/1/012047>.

This package provides useful functions which are needed for bioinformatic analysis such as calculating linear principal components from numeric data and Single-nucleotide polymorphism (SNP) dataset, calculating fixation index (Fst) using Hudson method, creating scatter plots in 3 views, handling with PLINK binary file format, detecting rough structures and outliers using unsupervised clustering, and calculating matrix multiplication in the faster way for big data.

Training and evaluating k-gram language models in R, supporting several probability smoothing techniques, perplexity computations, random text generation and more.

This package provides functions to identify plausible and replicable factor structures for a set of variables via k-fold cross validation. The process combines the exploratory and confirmatory factor analytic approach to scale development (Flora & Flake, 2017) <doi:10.1037/cbs0000069> with a cross validation technique that maximizes the available data (Hastie, Tibshirani, & Friedman, 2009) <isbn:978-0-387-21606-5>. Also available are functions to determine k by drawing on power analytic techniques for covariance structures (MacCallum, Browne, & Sugawara, 1996) <doi:10.1037/1082-989X.1.2.130>, generate model syntax, and summarize results in a report.

This package implements k-means like blockmodeling of one-mode and linked networks as presented in Žiberna (2020) <doi:10.1016/j.socnet.2019.10.006>. The development of this package is financially supported by the Slovenian Research Agency (<https://www.arrs.si/>) within the research programs P5-0168 and the research projects J7-8279 (Blockmodeling multilevel and temporal networks) and J5-2557 (Comparison and evaluation of different approaches to blockmodeling dynamic networks by simulations with application to Slovenian co-authorship networks).

This package provides a collection of personal helper functions to avoid redundancy in the spirit of the "Don't repeat yourself" principle of software development (<https://en.wikipedia.org/wiki/Don%27t_repeat_yourself>).

This package implements a quantified approach to the Kraljic Matrix (Kraljic, 1983, <https://hbr.org/1983/09/purchasing-must-become-supply-management>) for strategically analyzing a firmâ s purchasing portfolio. It combines multi-objective decision analysis to measure purchasing characteristics and uses this information to place products and services within the Kraljic Matrix.

Kernel Learning Integrative Clustering (KLIC) is an algorithm that allows to combine multiple kernels, each representing a different measure of the similarity between a set of observations. The contribution of each kernel on the final clustering is weighted according to the amount of information carried by it. As well as providing the functions required to perform the kernel-based clustering, this package also allows the user to simply give the data as input: the kernels are then built using consensus clustering. Different strategies to choose the best number of clusters are also available. For further details please see Cabassi and Kirk (2020) <doi:10.1093/bioinformatics/btaa593>.

This package provides methods for selecting the optimal bandwidth in kernel density estimation for dependent samples, such as those generated by Markov chain Monte Carlo (MCMC). Implements a modified biased cross-validation (mBCV) approach that accounts for sample dependence, improving the accuracy of estimated density functions.

One-way and two-way analysis of variance for replicated point patterns, grouped by one or two classification factors, on the basis of the corresponding K-functions.

Efficient implementation of Kernel SHAP (Lundberg and Lee, 2017, <doi:10.48550/arXiv.1705.07874>) permutation SHAP, and additive SHAP for model interpretability. For Kernel SHAP and permutation SHAP, if the number of features is too large for exact calculations, the algorithms iterate until the SHAP values are sufficiently precise in terms of their standard errors. The package integrates smoothly with meta-learning packages such as tidymodels', caret or mlr3'. It supports multi-output models, case weights, and parallel computations. Visualizations can be done using the R package shapviz'.

This package provides a method for detecting outliers with a Kalman filter on impulsed noised outliers and prediction on cleaned data. kfino is a robust sequential algorithm allowing to filter data with a large number of outliers. This algorithm is based on simple latent linear Gaussian processes as in the Kalman Filter method and is devoted to detect impulse-noised outliers. These are data points that differ significantly from other observations. ML (Maximization Likelihood) and EM (Expectation-Maximization algorithm) algorithms were implemented in kfino'. The method is described in full details in the following arXiv e-Print: <arXiv:2208.00961>.

We developed a package Keyboard for designing single-agent, drug-combination, or phase I/II dose-finding clinical trials. The Keyboard designs are novel early phase trial designs that can be implemented simply and transparently, similar to the 3+3 design, but yield excellent performance, comparable to those of more-complicated, model-based designs (Yan F, Mandrekar SJ, Yuan Y (2017) <doi:10.1158/1078-0432.CCR-17-0220>, Li DH, Whitmore JB, Guo W, Ji Y. (2017) <doi:10.1158/1078-0432.CCR-16-1125>, Liu S, Johnson VE (2016) <doi:10.1093/biostatistics/kxv040>, Zhou Y, Lee JJ, Yuan Y (2019) <doi:10.1002/sim.8475>, Pan H, Lin R, Yuan Y (2020) <doi:10.1016/j.cct.2020.105972>). The Keyboard package provides tools for designing, conducting, and analyzing single-agent, drug-combination, and phase I/II dose-finding clinical trials. For more details about how to use this packge, please refer to Li C, Sun H, Cheng C, Tang L, and Pan H. (2022) "A software tool for both the maximum tolerated dose and the optimal biological dose finding trials in early phase designs". Manuscript submitted for publication.

The kernelized version of principal component analysis (KPCA) has proven to be a valid nonlinear alternative for tackling the nonlinearity of biological sample spaces. However, it poses new challenges in terms of the interpretability of the original variables. kpcaIG aims to provide a tool to select the most relevant variables based on the kernel PCA representation of the data as in Briscik et al. (2023) <doi:10.1186/s12859-023-05404-y>. It also includes functions for 2D and 3D visualization of the original variables (as arrows) into the kernel principal components axes, highlighting the contribution of the most important ones.

This package provides a weighting approach that employs kernels to make one group have a similar distribution to another group on covariates. This method matches not only means or marginal distributions but also higher-order transformations implied by the choice of kernel. kbal is applicable to both treatment effect estimation and survey reweighting problems. Based on Hazlett, C. (2020) "Kernel Balancing: A flexible non-parametric weighting procedure for estimating causal effects." Statistica Sinica. <https://www.researchgate.net/publication/299013953_Kernel_Balancing_A_flexible_non-parametric_weighting_procedure_for_estimating_causal_effects>.

The developed function is designed to facilitate the seamless conversion of KML (Keyhole Markup Language) files to Shapefiles while preserving attribute values. It provides a straightforward interface for users to effortlessly import KML data, extract relevant attributes, and export them into the widely compatible Shapefile format. The package ensures accurate representation of spatial data while maintaining the integrity of associated attribute information. For details see, Flores, G. (2021). <DOI:10.1007/978-3-030-63665-4_15>. Whether for spatial analysis, visualization, or data interoperability, it simplifies the conversion process and empowers users to seamlessly work with geospatial datasets.

This package provides a seamless bridge between keras and the tidymodels frameworks. It allows for the dynamic creation of parsnip model specifications for keras models.

Estimates kriging models for geographical point-referenced data. Method is described in Gill (2020) <doi:10.1177/1532440020930197>.

Given constraints for right censored data, we use a recursive computational algorithm to calculate the the "constrained" Kaplan-Meier estimator. The constraint is assumed given in linear estimating equations or mean functions. We also illustrate how this leads to the empirical likelihood ratio test with right censored data and accelerated failure time model with given coefficients. EM algorithm from emplik package is used to get the initial value. The properties and performance of the EM algorithm is discussed in Mai Zhou and Yifan Yang (2015)<doi: 10.1007/s00180-015-0567-9> and Mai Zhou and Yifan Yang (2017) <doi: 10.1002/wics.1400>. More applications could be found in Mai Zhou (2015) <doi: 10.1201/b18598>.

An efficient algorithm inspired by majorization-minimization principle for solving the entire solution path of a flexible nonparametric expectile regression estimator constructed in a reproducing kernel Hilbert space.

Time Series Analysis including break detection, spectral analysis, KZ Fourier Transforms.