abn: Modelling Multivariate Data with Additive Bayesian Networks
Version 1.0.2

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 modelling, 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 generalised linear modelling (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 model of data from interdependent variables. Laplace approximations are used to estimate goodness of fit metrics and model parameters, and wrappers are also included to the INLA package which can be obtained from . It is recommended the testing version, which can be downloaded by running: source("http://www.math.ntnu.no/inla/givemeINLA-testing.R"). A comprehensive set of documented case studies, numerical accuracy/quality assurance exercises, and additional documentation are available from the 'abn' website.

Browse man pages Browse package API and functions Browse package files

AuthorFraser Ian Lewis [aut], Gilles Kratzer [cre, ctb], Marta Pittavino [ctb], Reinhard Furrer [ctb]
Date of publication2016-11-09 23:38:50
MaintainerGilles Kratzer <gilles.kratzer@math.uzh.ch>
LicenseGPL (>= 2)
Version1.0.2
URL http://www.r-bayesian-networks.org
Package repositoryView on CRAN
InstallationInstall the latest version of this package by entering the following in R:
install.packages("abn")

Man pages

abninla-internal: abn internal functions
build_score_cache: Build a cache of goodness of fit metrics for each node in a...
dag_ex0: Synthetic validation data set for use with abn library...
dag_ex1: Synthetic validation data set for use with abn library...
dag_ex2: Synthetic validation data set for use with abn library...
dag_ex3: Validation data set for use with abn library examples
dag_ex4: Valdiation data set for use with abn library examples
dag_ex5: Valdiation data set for use with abn library examples
dag_ex6: Valdiation data set for use with abn library examples
dag_ex7: Valdiation data set for use with abn library examples
fitabn: Fit an additive Bayesian network model
mostprobable: Find most probable DAG structure
pigs.vienna: Dataset related to diseases present in 'finishing pigs',...
search_hillclimber: Find high scoring directed acyclic graphs using heuristic...
tographviz: Convert a dag into graphviz format
var33: simulated dataset from a DAG comprising of 33 variables

Functions

buildscorecache Man page Source code
calc.node.inla.glm Man page Source code
calc.node.inla.glmm Man page Source code
check.valid.dag Source code
check.valid.data Source code
check.valid.groups Source code
check.valid.parents Source code
check.which.valid.nodes Source code
eval.across.grid Source code
ex0.dag.data Man page
ex1.dag.data Man page
ex2.dag.data Man page
ex3.dag.data Man page
ex4.dag.data Man page
ex5.dag.data Man page
ex6.dag.data Man page
ex7.dag.data Man page
find.next.left.x Source code
find.next.right.x Source code
fitabn Man page Source code
get.ind.quantiles Source code
get.quantiles Source code
get.var.types Source code
getMargsINLA Source code
getModeVector Source code
getmarginals Source code
graphicsetup Source code
mostprobable Man page Source code
pigs.vienna Man page
search.hillclimber Man page Source code
std.area.under.grid Source code
tidy.cache Source code
tographviz Man page Source code
var33 Man page

Files

inst
inst/tests
inst/tests/test.R
inst/tests/testdata
inst/tests/testdata/fitabn_ex0.Rdata
inst/tests/testdata/buildscorecache_ex1.Rdata
inst/doc
inst/doc/abn_v1.0.2.R
inst/doc/abn_v1.0.2.pdf
inst/doc/abn_v1.0.2.Rnw
inst/bootstrapping_example
inst/bootstrapping_example/inits.R
inst/bootstrapping_example/10Kbootstrapping.bash
inst/bootstrapping_example/Pigs_PostBootPlots.pdf
inst/bootstrapping_example/simulate_1par.bug
inst/bootstrapping_example/MargPlots_PigsData.pdf
inst/bootstrapping_example/script1.R
inst/bootstrapping_example/inits_2.R
inst/bootstrapping_example/analysis_jags_output.R
inst/bootstrapping_example/inits_1.R
inst/bootstrapping_example/10KBootstrapping.R
inst/bootstrapping_example/initsearch.bash
inst/bootstrapping_example/pigs_model.bug
inst/bootstrapping_example/pigs_post_params.R
inst/bootstrapping_example/jags_pigs_script.R
inst/bootstrapping_example/calculate_marginalDensities.R
configure.ac
src
src/node_binomial_marginals_rv.c
src/node_gaussian_rv_inner.c
src/node_gaussian.h
src/makefile.custom
src/cycles.h
src/node_poisson.h
src/fit_single_node.c
src/searchhill.c
src/node_gaussian_marginals_rv.h
src/buildcachematrix.c
src/node_poisson_marginals_rv.h
src/node_gaussian_rv_inner.h
src/node_binomial_rv_inner.c
src/node_binomial_rv.c
src/utility.h
src/node_gaussian_rv.c
src/node_poisson_rv_inner.h
src/node_poisson_marginals_rv.c
src/fit_single_node.h
src/fitabn_marginals.h
src/structs.h
src/node_binomial.h
src/node_gaussian.c
src/cycles.c
src/Makevars.in
src/node_binomial_marginals_rv.h
src/node_poisson_rv.h
src/node_poisson_rv_inner.c
src/mostprobable.c
src/node_binomial_rv.h
src/searchhill.h
src/mobius.h
src/node_poisson_rv.c
src/node_binomial_rv_inner.h
src/buildcachematrix.h
src/Makevars.win
src/node_gaussian_marginals_rv.c
src/fitabn_marginals.c
src/node_binomial.c
src/node_poisson.c
src/utility.c
src/node_gaussian_rv.h
src/mobius.c
NAMESPACE
data
data/ex0data.RData
data/pigs.vienna.RData
data/ex2data.RData
data/ex6data.RData
data/ex7data.RData
data/ex5data.RData
data/var33.RData
data/ex1data.RData
data/ex4data.RData
data/ex3data.RData
R
R/search_hillclimber.R
R/getmarginals.R
R/calc_node_inla_glmm.R
R/mostprobable.R
R/abn-internal.R
R/tographviz.R
R/fitabn.R
R/calc_node_inla_glm.R
R/build_score_cache.R
vignettes
vignettes/map_1par.dot
vignettes/Pigs_PostBootPlots.pdf
vignettes/var33_MASTER.pdf
vignettes/postbootpigs.pdf
vignettes/mydag.dot
vignettes/MargPlots_PigsData.pdf
vignettes/Summary.png
vignettes/ComparisonOfNetworkScore.pdf
vignettes/plbinaryNode.png
vignettes/mydag.pdf
vignettes/map1_10var.dot
vignettes/mydag_all.pdf
vignettes/PigsArea.png
vignettes/abn_v1.0.2-concordance.tex
vignettes/DAG_cycle.pdf
vignettes/map1_10var.pdf
vignettes/Bootstrapping.png
vignettes/map1_10var.png
vignettes/dagcon.pdf
vignettes/mydagcts.pdf
vignettes/abn_v1.0.2.Rnw
vignettes/map_1par.pdf
vignettes/abn.bib
vignettes/dagcon.png
MD5
build
build/vignette.rds
DESCRIPTION
configure
ChangeLog
man
man/tographviz.Rd
man/dag_ex5.Rd
man/dag_ex4.Rd
man/dag_ex2.Rd
man/dag_ex6.Rd
man/dag_ex0.Rd
man/var33.Rd
man/dag_ex1.Rd
man/dag_ex3.Rd
man/dag_ex7.Rd
man/pigs.vienna.Rd
man/fitabn.Rd
man/abninla-internal.Rd
man/mostprobable.Rd
man/search_hillclimber.Rd
man/build_score_cache.Rd
cleanup
abn documentation built on May 19, 2017, 10:48 p.m.