Efficient Leave-One-Out Cross-Validation and WAIC for Bayesian Models

Efficient approximate leave-one-out cross-validation (LOO) for Bayesian models fit using Markov chain Monte Carlo, as described in Vehtari, Gelman, and Gabry (2017) . The approximation uses Pareto smoothed importance sampling (PSIS), a new procedure for regularizing importance weights. As a byproduct of the calculations, we also obtain approximate standard errors for estimated predictive errors and for the comparison of predictive errors between models. The package also provides methods for using stacking and other model weighting techniques to average Bayesian predictive distributions.

Empirical Transition Matrix

The etm (empirical transition matrix) package permits to estimate the matrix of transition probabilities for any time-inhomogeneous multi-state model with finite state space using the Aalen-Johansen estimator. Functions for data preparation and for displaying are also included (Allignol et al., 2011 ). Functionals of the Aalen-Johansen estimator, e.g., excess length-of-stay in an intermediate state, can also be computed (Allignol et al. 2011 ).

Bayesian Latent Variable Analysis

Fit a variety of Bayesian latent variable models, including confirmatory factor analysis, structural equation models, and latent growth curve models. References: Merkle & Rosseel (2018) ; Merkle et al. (2021) .

Data Table Back-End for 'dplyr'

Provides a data.table backend for 'dplyr'. The goal of 'dtplyr' is to allow you to write 'dplyr' code that is automatically translated to the equivalent, but usually much faster, data.table code.

Analyzing Dendrometer Data

Various functions to import, verify, process and plot high-resolution dendrometer data using daily and stem-cycle approaches as described in Deslauriers et al, 2007 . For more details about the package please see: Van der Maaten et al. 2016 .

Vectorised Tools for URL Handling and Parsing

A toolkit for all URL-handling needs, including encoding and decoding, parsing, parameter extraction and modification. All functions are designed to be both fast and entirely vectorised. It is intended to be useful for people dealing with web-related datasets, such as server-side logs, although may be useful for other situations involving large sets of URLs.

Classification and Regression Tests

Provides wrapper functions for running classification and regression tests using different machine learning techniques, such as Random Forests and decision trees. The package provides standardized methods for preparing data to suit the algorithm's needs, training a model, making predictions, and evaluating results. Also, some functions are provided to run multiple instances of a test.

"Hit and Run" and "Shake and Bake" for Sampling Uniformly from Convex Shapes

The "Hit and Run" Markov Chain Monte Carlo method for sampling uniformly from convex shapes defined by linear constraints, and the "Shake and Bake" method for sampling from the boundary of such shapes. Includes specialized functions for sampling normalized weights with arbitrary linear constraints. Tervonen, T., van Valkenhoef, G., Basturk, N., and Postmus, D. (2012) . van Valkenhoef, G., Tervonen, T., and Postmus, D. (2014) .

Various Functions to Facilitate Visualization of Data and Analysis

When analyzing data, plots are a helpful tool for visualizing data and interpreting statistical models. This package provides a set of simple tools for building plots incrementally, starting with an empty plot region, and adding bars, data points, regression lines, error bars, gradient legends, density distributions in the margins, and even pictures. The package builds further on R graphics by simply combining functions and settings in order to reduce the amount of code to produce for the user. As a result, the package does not use formula input or special syntax, but can be used in combination with default R plot functions. Note: Most of the functions were part of the package 'itsadug', which is now split in two packages: 1. the package 'itsadug', which contains the core functions for visualizing and evaluating nonlinear regression models, and 2. the package 'plotfunctions', which contains more general plot functions.

Minimization Methods for Ill-Conditioned Problems

Implementation of methods for minimizing ill-conditioned problems. Currently only includes regularized (quasi-)newton optimization (Kanzow and Steck et al. (2023), ).