Forecasting univariate time series with ensemble empirical mode decomposition (EEMD) with long short-term memory (LSTM). For method details see Jaiswal, R. et al. (2022). <doi:10.1007/s00521-021-06621-3>.

The encompassing test is developed based on multi-step-ahead predictions of two nested models as in Pitarakis, J. (2023) <doi:10.48550/arXiv.2312.16099>. The statistics are standardised to a normal distribution, and the null hypothesis is that the larger model contains no additional useful information. P-values will be provided in the output.

Estimating individual-level covariate-outcome associations using aggregate data ("ecological inference") or a combination of aggregate and individual-level data ("hierarchical related regression").

This package provides a framework that provides the methods for quantifying entropy-based local indicator of spatial association (ELSA) that can be used for both continuous and categorical data. In addition, this package offers other methods to measure local indicators of spatial associations (LISA). Furthermore, global spatial structure can be measured using a variogram-like diagram, called entrogram. For more information, please check that paper: Naimi, B., Hamm, N. A., Groen, T. A., Skidmore, A. K., Toxopeus, A. G., & Alibakhshi, S. (2019) <doi:10.1016/j.spasta.2018.10.001>.

This package contains two functions that are intended to make tuning supervised learning methods easy. The eztune function uses a genetic algorithm or Hooke-Jeeves optimizer to find the best set of tuning parameters. The user can choose the optimizer, the learning method, and if optimization will be based on accuracy obtained through validation error, cross validation, or resubstitution. The function eztune.cv will compute a cross validated error rate. The purpose of eztune_cv is to provide a cross validated accuracy or MSE when resubstitution or validation data are used for optimization because error measures from both approaches can be misleading.

Testing for and dating periods of explosive dynamics (exuberance) in time series using the univariate and panel recursive unit root tests proposed by Phillips et al. (2015) <doi:10.1111/iere.12132> and Pavlidis et al. (2016) <doi:10.1007/s11146-015-9531-2>.The recursive least-squares algorithm utilizes the matrix inversion lemma to avoid matrix inversion which results in significant speed improvements. Simulation of a variety of periodically-collapsing bubble processes. Details can be found in Vasilopoulos et al. (2022) <doi:10.18637/jss.v103.i10>.

Implementation of Energy Trees, a statistical model to perform classification and regression with structured and mixed-type data. The model has a similar structure to Conditional Trees, but brings in Energy Statistics to test independence between variables that are possibly structured and of different nature. Currently, the package covers functions and graphs as structured covariates. It builds upon partykit to provide functionalities for fitting, printing, plotting, and predicting with Energy Trees. Energy Trees are described in Giubilei et al. (2022) <arXiv:2207.04430>.

This package provides data sets and R Codes for E.R. Williams, C.E. Harwood and A.C. Matheson (2023). Experimental Design and Analysis for Tree Improvement, CSIRO Publishing.

Pacote para a analise de experimentos havendo duas variaveis explicativas quantitativas e uma variavel dependente quantitativa. Os experimentos podem ser sem repeticoes ou com delineamento estatistico. Sao ajustados 12 modelos de regressao multipla e plotados graficos de superficie resposta (Hair JF, 2016) <ISBN:13:978-0138132637>.(Package for the analysis of experiments having two explanatory quantitative variables and one quantitative dependent variable. The experiments can be without repetitions or with a statistical design. Twelve multiple regression models are fitted and response surface graphs are plotted (Hair JF, 2016) <ISBN:13:978-0138132637>).

Recently many new p-value based multiple test procedures have been proposed, and these new methods are more powerful than the widely used Hochberg procedure. These procedures strongly control the familywise error rate (FWER). This is a comprehensive collection of p-value based FWER-control stepwise multiple test procedures, including six procedure families and thirty multiple test procedures. In this collection, the conservative Hochberg procedure, linear time Hommel procedures, asymptotic Rom procedure, Gou-Tamhane-Xi-Rom procedures, and Quick procedures are all developed in recent five years since 2014. The package name "elitism" is an acronym of "e"quipment for "l"ogarithmic and l"i"near "ti"me "s"tepwise "m"ultiple hypothesis testing. See Gou, J. (2022), "Quick multiple test procedures and p-value adjustments", Statistics in Biopharmaceutical Research 14(4), 636-650.

This package creates realistic random trajectories in a 3-D space between two given fix points, so-called conditional empirical random walks (CERWs). The trajectory generation is based on empirical distribution functions extracted from observed trajectories (training data) and thus reflects the geometrical movement characteristics of the mover. A digital elevation model (DEM), representing the Earth's surface, and a background layer of probabilities (e.g. food sources, uplift potential, waterbodies, etc.) can be used to influence the trajectories. Unterfinger M (2018). "3-D Trajectory Simulation in Movement Ecology: Conditional Empirical Random Walk". Master's thesis, University of Zurich. <https://www.geo.uzh.ch/dam/jcr:6194e41e-055c-4635-9807-53c5a54a3be7/MasterThesis_Unterfinger_2018.pdf>. Technitis G, Weibel R, Kranstauber B, Safi K (2016). "An algorithm for empirically informed random trajectory generation between two endpoints". GIScience 2016: Ninth International Conference on Geographic Information Science, 9, online. <doi:10.5167/uzh-130652>.

Analysis and visualization of similarities between epilepsy ontologies based on text mining results by comparing ranked lists of co-occurring drug terms in the BioASQ corpus. The ranked result lists of neurological drug terms co-occurring with terms from the epilepsy ontologies EpSO, ESSO, EPILONT, EPISEM and FENICS undergo further analysis. The source data to create the ranked lists of drug names is produced using the text mining workflows described in Mueller, Bernd and Hagelstein, Alexandra (2016) <doi:10.4126/FRL01-006408558>, Mueller, Bernd et al. (2017) <doi:10.1007/978-3-319-58694-6_22>, Mueller, Bernd and Rebholz-Schuhmann, Dietrich (2020) <doi:10.1007/978-3-030-43887-6_52>, and Mueller, Bernd et al. (2022) <doi:10.1186/s13326-021-00258-w>.

The confusion matrix (CM) is used to get a classifier's evaluation measure in order to select a method among many. A stochastic matrix and its transformation are computed from the CM. The eigenvalues of the transformed symmetric matrix are used to get an entropy which appears to be a good evaluation measure. Many other measures, commonly used, are provided for comparison purpose.

Detects sustained change in digital bio-marker data using simultaneous confidence bands. Accounts for noise using an auto-regressive model. Based on Buehlmann (1998) "Sieve bootstrap for smoothing in nonstationary time series" <doi:10.1214/aos/1030563978>.

Estimates extinction risk from population time series under a drifted Wiener process using MLE and observation-error-and-autocovariance-robust estimators, with confidence intervals based on the w-z method.

This package provides tools for exploring animal tracking data, from raw telemetry points to summaries, interactive maps, and home range estimates. It is designed to be beginner-friendly and requires minimal data wrangling.

The top-performing ensemble-based Penalized Cox Regression (ePCR) framework developed during the DREAM 9.5 mCRPC Prostate Cancer Challenge <https://www.synapse.org/ProstateCancerChallenge> presented in Guinney J, Wang T, Laajala TD, et al. (2017) <doi:10.1016/S1470-2045(16)30560-5> is provided here-in, together with the corresponding follow-up work. While initially aimed at modeling the most advanced stage of prostate cancer, metastatic Castration-Resistant Prostate Cancer (mCRPC), the modeling framework has subsequently been extended to cover also the non-metastatic form of advanced prostate cancer (CRPC). Readily fitted ensemble-based model S4-objects are provided, and a simulated example dataset based on a real-life cohort is provided from the Turku University Hospital, to illustrate the use of the package. Functionality of the ePCR methodology relies on constructing ensembles of strata in patient cohorts and averaging over them, with each ensemble member consisting of a highly optimized penalized/regularized Cox regression model. Various cross-validation and other modeling schema are provided for constructing novel model objects.

Survival analysis is employed to model time-to-event data. This package examines the relationship between survival and one or more predictors, termed as covariates, which can include both treatment variables (e.g., season of birth, represented by indicator functions) and continuous variables. To this end, the Cox-proportional hazard (Cox-PH) model, introduced by Cox in 1972, is a widely applicable and commonly used method for survival analysis. This package enables the estimation of the effect of randomization for the treatment variable to account for potential confounders, providing adjustment when estimating the association with exposure. It accommodates both fixed and time-dependent covariates and computes survival probabilities for lactation periods in dairy animals. The package is built upon the algorithm developed by Klein and Moeschberger (2003) <DOI:10.1007/b97377>.

Allows the user to determine minimum sample sizes that achieve target size and power at a specified alternative. For more information, see â Exact samples sizes for clinical trials subject to size and power constraintsâ by Lloyd, C.J. (2022) Preprint <doi:10.13140/RG.2.2.11828.94085>.

This package provides estimation utilities for binary Emax dose-response models. Includes Expectation-Maximization based maximum likelihood estimation when the binary response is missing, as well as bias-reduced estimators including Jeffreys-penalized likelihood, Firth-score, and Cox-Snell corrections.The methodology is described in Zhang, Pradhan, and Zhao (2025) <doi:10.1177/09622802251403356> and Zhang, Pradhan, and Zhao (2026) <doi:10.1080/10543406.2026.2627387>.

The production of certified reference materials (CRMs) requires various statistical tests depending on the task and recorded data to ensure that reported values of CRMs are appropriate. Often these tests are performed according to the procedures described in ISO GUIDE 35:2017'. The eCerto package contains a Shiny app which provides functionality to load, process, report and backup data recorded during CRM production and facilitates following the recommended procedures. It is described in Lisec et al (2023) <doi:10.1007/s00216-023-05099-3> and can also be accessed online <https://apps.bam.de/shn00/eCerto/> without package installation.

This package provides several functions to simplify using the glmnet package: converting data frames into matrices ready for glmnet'; b) imputing missing variables multiple times; c) fitting and applying prediction models straightforwardly; d) assigning observations to folds in a balanced way; e) cross-validate the models; f) selecting the most representative model across imputations and folds; and g) getting the relevance of the model regressors; as described in several publications: Solanes et al. (2022) <doi:10.1038/s41537-022-00309-w>, Palau et al. (2023) <doi:10.1016/j.rpsm.2023.01.001>, Salazar de Pablo et al. (2025) <doi:10.1038/s41380-025-03244-1>.

Computes the most important properties of four Bayesian early gating designs (two single arm and two randomized controlled designs), such as minimum required number of successes in the experimental group to make a GO decision, operating characteristics and average operating characteristics with respect to the sample size. These might aid in deciding what design to use for the early phase trial.

Error-driven learning (based on the Widrow & Hoff (1960)<https://isl.stanford.edu/~widrow/papers/c1960adaptiveswitching.pdf> learning rule, and essentially the same as Rescorla-Wagner's learning equations (Rescorla & Wagner, 1972, ISBN: 0390718017), which are also at the core of Naive Discrimination Learning, (Baayen et al, 2011, <doi:10.1037/a0023851>) can be used to explain bottom-up human learning (Hoppe et al, <doi:10.31234/osf.io/py5kd>), but is also at the core of artificial neural networks applications in the form of the Delta rule. This package provides a set of functions for building small-scale simulations to investigate the dynamics of error-driven learning and it's interaction with the structure of the input. For modeling error-driven learning using the Rescorla-Wagner equations the package ndl (Baayen et al, 2011, <doi:10.1037/a0023851>) is available on CRAN at <https://cran.r-project.org/package=ndl>. However, the package currently only allows tracing of a cue-outcome combination, rather than returning the learned networks. To fill this gap, we implemented a new package with a few functions that facilitate inspection of the networks for small error driven learning simulations. Note that our functions are not optimized for training large data sets (no parallel processing), as they are intended for small scale simulations and course examples. (Consider the python implementation pyndl <https://pyndl.readthedocs.io/en/latest/> for that purpose.).