Learning Bayesian Networks with Mixed Variables

Bayesian networks with continuous and/or discrete variables can be learned and compared from data. The method is described in Boettcher and Dethlefsen (2003), .

Borenstein Analysis

An implementation of the analysis about seed components from Borenstein et.al. 2008.

Component-Wise MOEA/D Implementation

Modular implementation of Multiobjective Evolutionary Algorithms based on Decomposition (MOEA/D) [Zhang and Li (2007), ] for quick assembling and testing of new algorithmic components, as well as easy replication of published MOEA/D proposals. The full framework is documented in a paper published in the Journal of Statistical Software [].

Create Visualisations for BART Models

Investigating and visualising Bayesian Additive Regression Tree (BART) (Chipman, H. A., George, E. I., & McCulloch, R. E. 2010) model fits. We construct conventional plots to analyze a model’s performance and stability as well as create new tree-based plots to analyze variable importance, interaction, and tree structure. We employ Value Suppressing Uncertainty Palettes (VSUP) to construct heatmaps that display variable importance and interactions jointly using colour scale to represent posterior uncertainty. Our visualisations are designed to work with the most popular BART R packages available, namely 'BART' Rodney Sparapani and Charles Spanbauer and Robert McCulloch 2021 , 'dbarts' (Vincent Dorie 2023) < https://CRAN.R-project.org/package=dbarts>, and 'bartMachine' (Adam Kapelner and Justin Bleich 2016) .

Calculates the Bidimensional Regression Between Two 2D Configurations

Calculates the bidimensional regression between two 2D configurations following the approach by Tobler (1965).

Bayesian Statistics for 2D/3D Transformations

Fits 2D and 3D geometric transformations via 'Stan' probabilistic programming engine ( Stan Development Team (2021) < https://mc-stan.org>). Returns posterior distribution for individual parameters of the fitted distribution. Allows for computation of LOO and WAIC information criteria (Vehtari A, Gelman A, Gabry J (2017) ) as well as Bayesian R-squared (Gelman A, Goodrich B, Gabry J, and Vehtari A (2018) ).

Create Scatter Plots with Marginal Density or Box Plots

Allows you to make clean, good-looking scatter plots with the option to easily add marginal density or box plots on the axes. It is also available as a module for 'jamovi' (see < https://www.jamovi.org> for more information). 'Scatr' is based on the 'cowplot' package by Claus O. Wilke and the 'ggplot2' package by Hadley Wickham.

HMMs with Ordered Hidden States and Emission Densities

Inference using a class of Hidden Markov models (HMMs) called 'oHMMed'(ordered HMM with emission densities ): The 'oHMMed' algorithms identify the number of comparably homogeneous regions within observed sequences with autocorrelation patterns. These are modelled as discrete hidden states; the observed data points are then realisations of continuous probability distributions with state-specific means that enable ordering of these distributions. The observed sequence is labelled according to the hidden states, permitting only neighbouring states that are also neighbours within the ordering of their associated distributions. The parameters that characterise these state-specific distributions are then inferred. Relevant for application to genomic sequences, time series, or any other sequence data with serial autocorrelation.

Tools for Causal Discovery on Observational Data

Various tools for inferring causal models from observational data. The package includes an implementation of the temporal Peter-Clark (TPC) algorithm. Petersen, Osler and Ekstrøm (2021) . It also includes general tools for evaluating differences in adjacency matrices, which can be used for evaluating performance of causal discovery procedures.

Decision Tree Analysis for Probabilistic Subgroup Identification with Multiple Treatments

In the situation when multiple alternative treatments or interventions available, different population groups may respond differently to different treatments. This package implements a method that discovers the population subgroups in which a certain treatment has a better effect than the other alternative treatments. This is done by first estimating the treatment effect for a given treatment and its uncertainty by computing random forests, and the resulting model is summarized by a decision tree in which the probabilities that the given treatment is best for a given subgroup is shown in the corresponding terminal node of the tree.