Learn R Programming

⚠️There's a newer version (3.1.1) of this package.Take me there.

abn (version 2.7-5)

Modelling Multivariate Data with Additive Bayesian Networks

Description

Bayesian network analysis is a form of probabilistic graphical models which derives from empirical data a directed acyclic graph, DAG, describing the dependency structure between random variables. An additive Bayesian network model consists of a form of a DAG where each node comprises a generalized linear model, GLM. Additive Bayesian network models are equivalent to Bayesian multivariate regression using graphical modeling; they generalises the usual multivariable regression, GLM, to multiple dependent variables. 'abn' provides routines to help determine optimal Bayesian network models for a given data set, where these models are used to identify statistical dependencies in messy, complex data. The additive formulation of these models is equivalent to multivariate generalized linear modeling (including mixed models with iid random effects). The usual term to describe this model selection process is structure discovery. The core functionality is concerned with model selection - determining the most robust empirical data model from interdependent variables. Laplace approximations are used to estimate the goodness of fit metrics and model parameters, and wrappers are included for the INLA package, which can be obtained from . The computing library JAGS is used to simulate 'abn'-like data. Detailed documentation, including documented case studies, numerical accuracy/quality assurance exercises, etc., is given in Kratzer et al. (2023) and on the website .

Copy Link

Version

Install

install.packages('abn')

Monthly Downloads

819

Version

2.7-5

License

GPL (>= 2)

Maintainer

Matteo Delucchi

Last Published

May 22nd, 2023

Functions in abn (2.7-5)

ex2.dag.data

Synthetic validation data set for use with abn library examples
ex3.dag.data

Validation data set for use with abn library examples
ex6.dag.data

Valdiation data set for use with abn library examples
ex7.dag.data

Valdiation data set for use with abn library examples
ex5.dag.data

Valdiation data set for use with abn library examples
ex4.dag.data

Valdiation data set for use with abn library examples
entropyData

Computes an Empirical Estimation of the Entropy from a Table of Counts
discretization

Discretization of a Possibly Continuous Data Frame of Random Variables based on their distribution
ex1.dag.data

Synthetic validation data set for use with abn library examples
ex0.dag.data

Synthetic validation data set for use with abn library examples
linkStrength

A function that returns the strengths of the edge connections in a Bayesian Network learned from observational data.
fit.control

Control the iterations in fitAbn
mostprobable

Find most probable DAG structure
mb

Compute the Markov blanket
expit

Expit, Logit, and odds
miData

Empirical Estimation of the Entropy from a Table of Counts
fitabn

Fit an additive Bayesian network model
infoDag

Compute standard information for a DAG.
or

Odds Ratio from a Table
essentialGraph

Construct the essential graph
searchHillclimber

Find high scoring directed acyclic graphs using heuristic search.
searchHeuristic

A family of heuristic algorithms that aims at finding high scoring directed acyclic graphs
scoreContribution

Compute the score's contribution in a network of each observation.
var33

simulated dataset from a DAG comprising of 33 variables
pigs.vienna

Dataset related to diseases present in `finishing pigs', animals about to enter the human food chain at an abattoir.
simulateAbn

Simulate from an ABN Network
tographviz

Convert a DAG into graphviz format
plotabn

Plot an ABN graphic
simulateDag

Simulate DAGs
version

abn Version Information
createDag

Create a legitimate DAGs
build.control

Control the iterations in buildScoreCache
compareDag

Compare two DAGs or EGs
FCV

Dataset related to Feline calicivirus infection among cats in Switzerland.
abn-deprecated

Deprecated functions and data in package abn
abn-defunct

Defunct functions and data in package abn
. abn .

abn Package
abn-internal

abn internal functions
adg

Dataset related to average daily growth performance and abattoir findings in pigs commercial production.
buildScoreCache

Build a cache of goodness of fit metrics for each node in a DAG, possibly subject to user-defined restrictions