Estimators for semi-parametric linear regression models with truncated response variables (fixed truncation point). The estimators implemented are the Symmetrically Trimmed Least Squares (STLS) estimator introduced by Powell (1986) <doi:10.2307/1914308>, the Quadratic Mode (QME) estimator introduced by Lee (1993) <doi:10.1016/0304-4076(93)90056-B>, and the Left Truncated (LT) estimator introduced by Karlsson (2006) <doi:10.1007/s00184-005-0023-x>.

Time series forecasting faces challenges due to the non-stationarity, nonlinearity, and chaotic nature of the data. Traditional deep learning models like Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) process data sequentially but are inefficient for long sequences. To overcome the limitations of these models, we proposed a transformer-based deep learning architecture utilizing an attention mechanism for parallel processing, enhancing prediction accuracy and efficiency. This paper presents user-friendly code for the implementation of the proposed transformer-based deep learning architecture utilizing an attention mechanism for parallel processing. References: Nayak et al. (2024) <doi:10.1007/s40808-023-01944-7> and Nayak et al. (2024) <doi:10.1016/j.simpa.2024.100716>.

Calculation of string distance following the tidy data principles. Built on top of the stringdist package.

This package provides functions that compute predictions from Generalised Additive Models (GAMs) fitted with mgcv and return them as a tibble. These can be plotted with a generic plot()-method that uses ggplot2 or plotted as any other data frame. The main function is predict_gam().

Extends invariant causal prediction (Peters et al., 2016, <doi:10.1111/rssb.12167>) to generalized linear and transformation models (Hothorn et al., 2018, <doi:10.1111/sjos.12291>). The methodology is described in Kook et al. (2023, <doi:10.1080/01621459.2024.2395588>).

Write output (plots and tables) ensuring traceability back to code. Includes a graphics saver with simple automation of stamping with source, destination and creation time. A list of plots can be saved at once. A user-friendly selection of output dimensions for presentations, on-screen inspections, and more available.

This package infers the V genotype of an individual from immunoglobulin (Ig) repertoire sequencing data (AIRR-Seq, Rep-Seq). Includes detection of any novel alleles. This information is then used to correct existing V allele calls from among the sample sequences. Citations: Gadala-Maria, et al (2015) <doi:10.1073/pnas.1417683112>, Gadala-Maria, et al (2019) <doi:10.3389/fimmu.2019.00129>.

First - Generates (potentially high-dimensional) high-frequency and low-frequency series for simulation studies in temporal disaggregation; Second - a toolkit utilizing temporal disaggregation and benchmarking techniques with a low-dimensional matrix of indicator series previously proposed in Dagum and Cholette (2006, ISBN:978-0-387-35439-2) ; and Third - novel techniques proposed by Mosley, Gibberd and Eckley (2021) <arXiv:2108.05783> for disaggregating low-frequency series in the presence of high-dimensional indicator matrices.

Multiple flavors of the Generalized Autoregressive Conditional Heteroskedasticity (GARCH) model with a large choice of conditional distributions. Methods for specification, estimation, prediction, filtering, simulation, statistical testing and more. Represents a partial re-write and re-think of rugarch', making use of automatic differentiation for estimation.

Changepoint detection algorithms for R are widespread but have different interfaces and reporting conventions. This makes the comparative analysis of results difficult. We solve this problem by providing a tidy, unified interface for several different changepoint detection algorithms. We also provide consistent numerical and graphical reporting leveraging the broom and ggplot2 packages.

An implementation of hypothesis testing in an extended Rasch modeling framework, including sample size planning procedures and power computations. Provides 4 statistical tests, i.e., gradient test (GR), likelihood ratio test (LR), Rao score or Lagrange multiplier test (RS), and Wald test, for testing a number of hypotheses referring to the Rasch model (RM), linear logistic test model (LLTM), rating scale model (RSM), and partial credit model (PCM). Three types of functions for power and sample size computations are provided. Firstly, functions to compute the sample size given a user-specified (predetermined) deviation from the hypothesis to be tested, the level alpha, and the power of the test. Secondly, functions to evaluate the power of the tests given a user-specified (predetermined) deviation from the hypothesis to be tested, the level alpha of the test, and the sample size. Thirdly, functions to evaluate the so-called post hoc power of the tests. This is the power of the tests given the observed deviation of the data from the hypothesis to be tested and a user-specified level alpha of the test. Power and sample size computations are based on a Monte Carlo simulation approach. It is computationally very efficient. The variance of the random error in computing power and sample size arising from the simulation approach is analytically derived by using the delta method. Additionally, functions to compute the power of the tests as a function of an effect measure interpreted as explained variance are provided. Draxler, C., & Alexandrowicz, R. W. (2015), <doi:10.1007/s11336-015-9472-y>.

This package provides functions to support economic modelling in R based on the methods of the Dutch guideline for economic evaluations in healthcare <https://www.zorginstituutnederland.nl/documenten/2024/01/16/richtlijn-voor-het-uitvoeren-van-economische-evaluaties-in-de-gezondheidszorg>, CBS data <https://www.cbs.nl/>, and OECD data <https://www.oecd.org/en.html>.

This package provides functionalities based on the paper "Time Varying Dictionary and the Predictive Power of FED Minutes" (Lima, 2018) <doi:10.2139/ssrn.3312483>. It selects the most predictive terms, that we call time-varying dictionary using supervised machine learning techniques as lasso and elastic net.

We propose an optimality criterion to determine the required training set, r-score, which is derived directly from Pearson's correlation between the genomic estimated breeding values and phenotypic values of the test set <doi:10.1007/s00122-019-03387-0>. This package provides two main functions to determine a good training set and its size.

Combine a list of taxa with a phylogeny to generate a starting tree for use in total evidence dating analyses.

This package provides functions for analyzing citizens bicycle usage pattern and predicting rental amount on specific conditions. Functions on this package interacts with data on tashudata package, a drat repository. tashudata package contains rental/return history on public bicycle system('Tashu'), weather for 3 years and bicycle station information. To install this data package, see the instructions at <https://github.com/zeee1/Tashu_Rpackage>. top10_stations(), top10_paths() function visualizes image showing the most used top 10 stations and paths. daily_bike_rental() and monthly_bike_rental() shows daily, monthly amount of bicycle rental. create_train_dataset(), create_test_dataset() is data processing function for prediction. Bicycle rental history from 2013 to 2014 is used to create training dataset and that on 2015 is for test dataset. Users can make random-forest prediction model by using create_train_model() and predict amount of bicycle rental in 2015 by using predict_bike_rental().

Estimation of time-dependent ROC curve and area under time dependent ROC curve (AUC) in the presence of censored data, with or without competing risks. Confidence intervals of AUCs and tests for comparing AUCs of two rival markers measured on the same subjects can be computed, using the iid-representation of the AUC estimator. Plot functions for time-dependent ROC curves and AUC curves are provided. Time-dependent Positive Predictive Values (PPV) and Negative Predictive Values (NPV) can also be computed. See Blanche et al. (2013) <doi:10.1002/sim.5958> and references therein for the details of the methods implemented in the package.

This package provides a mathematical optimization procedure in combination with statistical bootstrap for the estimation of the latent signals (sometimes called scores) informing the global consensus ranking (often named aggregation ranking). To solve mid/large-scale problems, users should install the gurobi optimiser (available from <https://www.gurobi.com/>).

Analyze lines of R code using tidy principles. This allows you to input lines of R code and output a data frame with one row per function included. Additionally, it facilitates code classification via included lexicons.

This package provides a simple interface to search available data provided by Theia (<https://theia.cnes.fr>), download it, and manage it. Data can be downloaded based on a search result or from a cart file downloaded from Theia website.

Finding the best values for user-specified arguments of a prediction algorithm can be difficult, particularly if there is an interaction between argument levels. This package automates the testing of any user-defined prediction algorithm over an arbitrary number of arguments. It includes functions for testing the algorithm over the given arguments with respect to an arbitrary number of user-defined diagnostics, visualising the results of these tests, and finding the optimal argument combinations with respect to each diagnostic.

Partially penalized versions of specific transformation models implemented in package mlt'. Available models include a fully parametric version of the Cox model, other parametric survival models (Weibull, etc.), models for binary and ordered categorical variables, normal and transformed-normal (Box-Cox type) linear models, and continuous outcome logistic regression. Hyperparameter tuning is facilitated through model-based optimization functionalities from package mlrMBO'. The accompanying vignette describes the methodology used in tramnet in detail. Transformation models and model-based optimization are described in Hothorn et al. (2019) <doi:10.1111/sjos.12291> and Bischl et al. (2016) <doi:10.48550/arXiv.1703.03373>, respectively.

An R shiny app designed for diverse text analysis tasks, offering a wide range of methodologies tailored to Natural Language Processing (NLP) needs. It is a versatile, general-purpose tool for analyzing textual data. tall features a comprehensive workflow, including data cleaning, preprocessing, statistical analysis, and visualization, all integrated for effective text analysis.

Finds the posterior modes for the mean and standard deviation for a truncated normal distribution with one or two known truncation points. The method used extends Bayesian methods for parameter estimation for a singly truncated normal distribution under the Jeffreys prior (see Zhou X, Giacometti R, Fabozzi FJ, Tucker AH (2014). "Bayesian estimation of truncated data with applications to operational risk measurement". <doi:10.1080/14697688.2012.752103>). This package additionally allows for a doubly truncated normal distribution.