This package contains a function to categorize accelerometer readings collected in free-living (e.g., for 24 hours/day for 7 days), preprocessed and compressed as counts (unit-less value) in a specified time period termed epoch (e.g., 1 minute) as either bedrest (sleep) or active. The input is a matrix with a timestamp column and a column with number of counts per epoch. The output is the same dataframe with an additional column termed bedrest. In the bedrest column each line (epoch) contains a function-generated classification br or a denoting bedrest/sleep and activity, respectively. The package is designed to be used after wear/nonwear marking function in the PhysicalActivity package. Version 1.1 adds preschool thresholds and corrects for possible errors in algorithm implementation.

Based on Dutta et al. (2018) <doi:10.1016/j.jempfin.2018.02.004>, this package provides their standardized test for abnormal returns in long-horizon event studies. The methods used improve the major weaknesses of size, power, and robustness of long-run statistical tests described in Kothari/Warner (2007) <doi:10.1016/B978-0-444-53265-7.50015-9>. Abnormal returns are weighted by their statistical precision (i.e., standard deviation), resulting in abnormal standardized returns. This procedure efficiently captures the heteroskedasticity problem. Clustering techniques following Cameron et al. (2011) <doi:10.1198/jbes.2010.07136> are adopted for computing cross-sectional correlation robust standard errors. The statistical tests in this package therefore accounts for potential biases arising from returns cross-sectional correlation, autocorrelation, and volatility clustering without power loss.

This package performs Geometrical Archetypal Analysis after creating Grid Archetypes which are the Cartesian Product of all minimum, maximum variable values. Since the archetypes are fixed now, we have the ability to compute the convex composition coefficients for all our available data points much faster by using the half part of Principal Convex Hull Archetypal method. Additionally we can decide to keep as archetypes the closer to the Grid Archetypes ones. Finally the number of archetypes is always 2 to the power of the dimension of our data points if we consider them as a vector space. Cutler, A., Breiman, L. (1994) <doi:10.1080/00401706.1994.10485840>. Morup, M., Hansen, LK. (2012) <doi:10.1016/j.neucom.2011.06.033>. Christopoulos, DT. (2024) <doi:10.13140/RG.2.2.14030.88642>.

The data sets used in the online course ,,PogromcyDanych''. You can process data in many ways. The course Data Crunchers will introduce you to this variety. For this reason we will work on datasets of different size (from several to several hundred thousand rows), with various level of complexity (from two to two thousand columns) and prepared in different formats (text data, quantitative data and qualitative data). All of these data sets were gathered in a single big package called PogromcyDanych to facilitate access to them. It contains all sorts of data sets such as data about offer prices of cars, results of opinion polls, information about changes in stock market indices, data about names given to newborn babies, ski jumping results or information about outcomes of breast cancer patients treatment.

Reads the provenance collected by the rdtLite or rdt packages, or other tools providing compatible PROV JSON output, created by the execution of a script or a console session, and provides a human-readable summary identifying the input and output files, the scripts used (if any), errors and warnings produced, and the environment in which it was executed. It can also optionally package all the files into a zip file. The exact format of the PROV JSON file created by rdtLite and rdt is described in <https://github.com/End-to-end-provenance/ExtendedProvJson>. More information about rdtLite and associated tools is available at <https://github.com/End-to-end-provenance/> and Lerner, Boose, and Perez (2018), Using Introspection to Collect Provenance in R, Informatics, <doi: 10.3390/informatics5010012>.

RNNs are preferred for sequential data like time series, speech, text, etc. but when dealing with long range dependencies, vanishing gradient problems account for their poor performance. LSTM and GRU are effective solutions which are nothing but RNN networks with the abilities of learning both short-term and long-term dependencies. Their structural makeup enables them to remember information for a long period without any difficulty. LSTM consists of one cell state and three gates, namely, forget gate, input gate and output gate whereas GRU comprises only two gates, namely, reset gate and update gate. This package consists of three different functions for the application of RNN, LSTM and GRU to any time series data for its forecasting. For method details see Jaiswal, R. et al. (2022). <doi:10.1007/s00521-021-06621-3>.

Consider a possibly nonlinear nonparametric regression with p regressors. We provide evaluations by 13 methods to rank regressors by their practical significance or importance using various methods, including machine learning tools. Comprehensive methods are as follows. m6=Generalized partial correlation coefficient or GPCC by Vinod (2021)<doi:10.1007/s10614-021-10190-x> and Vinod (2022)<https://www.mdpi.com/1911-8074/15/1/32>. m7= a generalization of psychologists effect size incorporating nonlinearity and many variables. m8= local linear partial (dy/dxi) using the np package for kernel regressions. m9= partial (dy/dxi) using the NNS package. m10= importance measure using the NNS boost function. m11= Shapley Value measure of importance (cooperative game theory). m12 and m13= two versions of the random forest algorithm. Taraldsen's exact density for sampling distribution of correlations added.

Conduct multiple quantitative trait loci (QTL) and QTL-by-environment interaction (QEI) mapping via ordinary or compressed variance component mixed models with random- or fixed QTL/QEI effects. First, each position on the genome is detected in order to obtain a negative logarithm P-value curve against genome position. Then, all the peaks on each effect (additive or dominant) curve or on each locus curve are viewed as potential main-effect QTLs and QEIs, all their effects are included in a multi-locus model, their effects are estimated by both least angle regression and empirical Bayes (or adaptive lasso) in backcross and F2 populations, and true QTLs and QEIs are identified by likelihood radio test. See Zhou et al. (2022) <doi:10.1093/bib/bbab596> and Wen et al. (2018) <doi:10.1093/bib/bby058>.

Assists performing tip-dating of phylogenetic trees with BEAST BEAST is a popular software for phylogenetic analysis. The package assists the implementation of various phylogenetic tip- dating tests using BEAST. It contains two main functions. The first one allows preparing date randomization analyses, which assess the temporal signal of a data set. The second function allows performing leave-one-out analyses, which test for the consistency between independent calibration sequences and allow pinpointing those leading to potential bias. The included tutorial provides detailed step-by-step instructions. An expanded description of the package can be found in article: Rieux, A. and Khatchikian, C.E. (2017), TIPDATINGBEAST: an R package to assist the implementation of phylogenetic tip-dating tests using BEAST. Molecular Ecology Resources, 17: 608-613. <onlinelibrary.wiley.com/doi/full/10.1111/1755-0998.12603>.

This package provides helper functions for working with multiple Visium capture areas that overlap each other. This package was developed along with the companion example use case data available from https://github.com/LieberInstitute/visiumStitched_brain. visiumStitched prepares SpaceRanger (10x Genomics) output files so you can stitch the images from groups of capture areas together with Fiji. Then visiumStitched builds a SpatialExperiment object with the stitched data and makes an artificial hexogonal grid enabling the seamless use of spatial clustering methods that rely on such grid to identify neighboring spots, such as PRECAST and BayesSpace. The SpatialExperiment objects created by visiumStitched are compatible with spatialLIBD, which can be used to build interactive websites for stitched SpatialExperiment objects. visiumStitched also enables casting SpatialExperiment objects as Seurat objects.

Bayesian MCPMod (Fleischer et al. (2022) <doi:10.1002/pst.2193>) is an innovative method that improves the traditional MCPMod by systematically incorporating historical data, such as previous placebo group data. This R package offers functions for simulating, analyzing, and evaluating Bayesian MCPMod trials with normally distributed endpoints. It enables the assessment of trial designs incorporating historical data across various true dose-response relationships and sample sizes. Robust mixture prior distributions, such as those derived with the Meta-Analytic-Predictive approach (Schmidli et al. (2014) <doi:10.1111/biom.12242>), can be specified for each dose group. Resulting mixture posterior distributions are used in the Bayesian Multiple Comparison Procedure and modeling steps. The modeling step also includes a weighted model averaging approach (Pinheiro et al. (2014) <doi:10.1002/sim.6052>). Estimated dose-response relationships can be bootstrapped and visualized.

This package provides a study based on the screened selection design (SSD) is an exploratory phase II randomized trial with two or more arms but without concurrent control. The primary aim of the SSD trial is to pick a desirable treatment arm (e.g., in terms of the median survival time) to recommend to the subsequent randomized phase IIb (with the concurrent control) or phase III. Though The survival endpoint is often encountered in phase II trials, the existing SSD methods cannot deal with the survival endpoint. Furthermore, the existing SSD wonâ t control the type I error rate. The proposed designs can â partiallyâ control or provide the empirical type I error/false positive rate by an optimal algorithm (implemented by the optimal() function) for each arm. All the design needed components (sample size, operating characteristics) are supported.

Heuristic methods to solve the routing problems in a warehouse management. Package includes several heuristics such as the Midpoint, Return, S-Shape and Semi-Optimal Heuristics for designation of the pickerâ s route in order picking. The heuristics aim to provide the acceptable travel distances while considering warehouse layout constraints such as aisles and shelves. It also includes implementation of the COPRAS (COmplex PRoportional ASsessment) method for supporting selection of locations to be visited by the picker in shared storage systems. The package is designed to facilitate more efficient warehouse routing and logistics operations. see: Bartholdi, J. J., Hackman, S. T. (2019). "WAREHOUSE & DISTRIBUTION SCIENCE. Release 0.98.1." The Supply Chain & Logistics Institute. H. Milton Stewart School of Industrial and Systems Engineering. Georgia Institute of Technology. <https://www.warehouse-science.com/book/editions/wh-sci-0.98.1.pdf>.

Visualization of antibody titer scores is valuable for examination of vaccination effects. AntibodyTiters visualizes antibody titers of all or selected patients. This package also produces empty excel files in a specified format, in which users can fill in experimental data for visualization. Excel files with toy data can also be produced, so that users can see how it is visualized before obtaining real data. The data should contain titer scores at pre-vaccination, after-1st shot, after-2nd shot, and at least one additional sampling points. Patients with missing values can be included. The first two sampling points (pre-vaccination and after-1st shot) will be plotted discretely, whereas those following will be plotted on a continuous time scale that starts from the day of second shot. Half-life of titer can also be calculated for each pair of sampling points.

This package contains functions that allow Bayesian inference on a parameter of some widely-used exponential models. The functions can generate independent samples from the closed-form posterior distribution using the inverse stable prior. Inverse stable is a non-conjugate prior for a parameter of an exponential subclass of discrete and continuous data distributions (e.g. Poisson, exponential, inverse gamma, double exponential (Laplace), half-normal/half-Gaussian, etc.). The prior class provides flexibility in capturing a wide array of prior beliefs (right-skewed and left-skewed) as modulated by a parameter that is bounded in (0,1). The generated samples can be used to simulate the prior and posterior predictive distributions. More details can be found in Cahoy and Sedransk (2019) <doi:10.1007/s42519-018-0027-2>. The package can also be used as a teaching demo for introductory Bayesian courses.

This package provides tools for performing routine analysis and plotting tasks with environmental data from the System Wide Monitoring Program of the National Estuarine Research Reserve System <https://cdmo.baruch.sc.edu/>. This package builds on the functionality of the SWMPr package <https://cran.r-project.org/package=SWMPr>, which is used to retrieve and organize the data. The combined set of tools address common challenges associated with continuous time series data for environmental decision making, and are intended for use in annual reporting activities. References: Beck, Marcus W. (2016) <ISSN 2073-4859><https://journal.r-project.org/archive/2016-1/beck.pdf> Rudis, Bob (2014) <https://rud.is/b/2014/11/16/moving-the-earth-well-alaska-hawaii-with-r/>. United States Environmental Protection Agency (2015) <https://cfpub.epa.gov/si/si_public_record_Report.cfm?Lab=OWOW&dirEntryId=327030>.

Sample size estimations for MRMC studies based on the Obuchowski-Rockette (OR) methodology is implemented. The function can calculate sample sizes where the endpoint of interest in the study is either ROC AUC (Area-Under-the-Receiver-Operating-Characteristics-Curve) or sensitivity. The package can also return sample sizes for studies expected to have clustering effect (e.g.- multiple pulmonary nodules per patient). All calculations assume that the study design is fully crossed (paired-reader, paired-case) where each reader reads/interprets each case and that there are two interventions/imaging-modalities/techniques in the study. In addition to MRMC, it can also be used to estimate sample sizes for standalone studies where sensitivity or AUC are the primary endpoints. The methods implemented are based on the methods described in Zhou et.al. (2011) <doi:10.1002/9780470906514> and Obuchowski (2000) <doi:10.1097/EDE.0b013e3181a663cc>.

Speed up common tasks, particularly logical or relational comparisons and routine follow up tasks such as finding the indices and subsetting. Inspired by mathematics, where something like: 3 < x < 6 is a standard, elegant and clear way to assert that x is both greater than 3 and less than 6 (see for example <https://en.wikipedia.org/wiki/Relational_operator>), a chaining operator is implemented. The chaining operator, %c%, allows multiple relational operations to be used in quotes on the right hand side for the same object, on the left hand side. The %e% operator allows something like set-builder notation (see for example <https://en.wikipedia.org/wiki/Set-builder_notation>) to be used on the right hand side. All operators have built in prefixes defined for all, subset, and which to reduce the amount of code needed for common tasks, such as return those values that are true.

This package provides a supervised learning algorithm inputs a train set, and outputs a prediction function, which can be used on a test set. If each data point belongs to a subset (such as geographic region, year, etc), then how do we know if subsets are similar enough so that we can get accurate predictions on one subset, after training on Other subsets? And how do we know if training on All subsets would improve prediction accuracy, relative to training on the Same subset? SOAK, Same/Other/All K-fold cross-validation, <doi:10.48550/arXiv.2410.08643> can be used to answer these question, by fixing a test subset, training models on Same/Other/All subsets, and then comparing test error rates (Same versus Other and Same versus All). Also provides code for estimating how many train samples are required to get accurate predictions on a test set.

Enables computationally efficient parameters-estimation by variational Bayesian methods for various diagnostic classification models (DCMs). DCMs are a class of discrete latent variable models for classifying respondents into latent classes that typically represent distinct combinations of skills they possess. Recently, to meet the growing need of large-scale diagnostic measurement in the field of educational, psychological, and psychiatric measurements, variational Bayesian inference has been developed as a computationally efficient alternative to the Markov chain Monte Carlo methods, e.g., Yamaguchi and Okada (2020a) <doi:10.1007/s11336-020-09739-w>, Yamaguchi and Okada (2020b) <doi:10.3102/1076998620911934>, Yamaguchi (2020) <doi:10.1007/s41237-020-00104-w>, Oka and Okada (2023) <doi:10.1007/s11336-022-09884-4>, and Yamaguchi and Martinez (2023) <doi:10.1111/bmsp.12308>. To facilitate their applications, variationalDCM is developed to provide a collection of recently-proposed variational Bayesian estimation methods for various DCMs.

We present a range of simulations to aid researchers in determining appropriate sample sizes when performing critical thermal limits studies (e.g. CTmin/CTmin experiments). A number of wrapper functions are provided for plotting and summarising outputs from these simulations. This package is presented in van Steenderen, C.J.M., Sutton, G.F., Owen, C.A., Martin, G.D., and Coetzee, J.A. Sample size assessments for thermal physiology studies: An R package and R Shiny application. 2023. Physiological Entomology. <doi:10.1111/phen.12416>. The GUI version of this package is available on the R Shiny online server at: <https://clarkevansteenderen.shinyapps.io/ThermalSampleR_Shiny/> , or it is accessible via GitHub at <https://github.com/clarkevansteenderen/ThermalSampleR_Shiny/>. We would like to thank Grant Duffy (University of Otago, Dundedin, New Zealand) for granting us permission to use the source code for the Test of Total Equivalency function.

Compute the frequency distribution of a search term in a series of texts. For example, Arthur Conan Doyle wrote a total of 60 Sherlock Holmes stories, comprised of 54 short stories and 4 longer novels. I wanted to test my own subjective impression that, in many of the stories, Sherlock Holmes popularity was used as bait to induce the reader to read a story that is essentially not primarily a Sherlock Holmes story. I used the term "Holmes" as a search pattern, since Watson would frequently address him by name, or use his name to describe something that he was doing. My hypothesis is that the frequency distribution of the search pattern "Holmes" is a good proxy for the degree to which a story is or is not truly a Sherlock Holmes story. The results are presented in a manuscript that is available as a vignette and online at <https://barryzee.github.io/Concordance/index.html>.

This package provides functions for eleven procedures for determining the number of factors, including functions for parallel analysis and the minimum average partial test. There are also functions for conducting principal components analysis, principal axis factor analysis, maximum likelihood factor analysis, image factor analysis, and extension factor analysis, all of which can take raw data or correlation matrices as input and with options for conducting the analyses using Pearson correlations, Kendall correlations, Spearman correlations, gamma correlations, or polychoric correlations. Varimax rotation, promax rotation, and Procrustes rotations can be performed. Additional functions focus on the factorability of a correlation matrix, the congruences between factors from different datasets, the assessment of local independence, the assessment of factor solution complexity, and internal consistency. Auerswald & Moshagen (2019, ISSN:1939-1463); Field, Miles, & Field (2012, ISBN:978-1-4462-0045-2); Mulaik (2010, ISBN:978-1-4200-9981-2); O'Connor (2000, <doi:10.3758/bf03200807>); O'Connor (2001, ISSN:0146-6216).

Weather indices represent the overall weekly effect of a weather variable on crop yield throughout the cropping season. This package contains functions that can convert the weekly weather data into yearly weighted Weather indices with weights being the correlation coefficient between weekly weather data over the years and crop yield over the years. This can be done for an individual weather variable and for two weather variables at a time as the interaction effect. This method was first devised by Jain, RC, Agrawal R, and Jha, MP (1980), "Effect of climatic variables on rice yield and its forecast",MAUSAM, 31(4), 591â 596, <doi:10.54302/mausam.v31i4.3477>. Later, the method have been used by various researchers and the latest can found in Gupta, AK, Sarkar, KA, Dhakre, DS, & Bhattacharya, D (2022), "Weather Based Potato Yield Modelling using Statistical and Machine Learning Technique",Environment and Ecology, 40(3B), 1444â 1449,<https://www.environmentandecology.com/volume-40-2022>.