abn: Modelling Multivariate Data with Additive Bayesian Networks

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 <http://www.r-inla.org>. 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.

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
http://www.r-bayesian-networks.org

View on CRAN

Files

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

Questions? Problems? Suggestions? or email at ian@mutexlabs.com.

Please suggest features or report bugs with the GitHub issue tracker.

All documentation is copyright its authors; we didn't write any of that.