Graphical Independence Networks
Compile conditional probability tables / cliques potentials.
Chest clinic example
Extract conditional probabilities and clique potentials from data.
Create conditional probability tables (CPTs)
Evidence objects
Set, retrieve, and retract finding in Bayesian network.
gRain generics
Get superset for each element in a list
Graphical Independence Network
Simulate from an independence network
Compile a graphical independence network (a Bayesian network)
Set, update and remove evidence.
Set joint evidence in grain objects
Make predictions from a probabilistic network
Propagate a graphical independence network (a Bayesian network)
Wet grass example
Internal functions for the gRain package
Load and save Hugin net files
Conditional probability tables based on logical dependencies
Mendelian segregation
Query a network
Create repeated patterns in Bayesian networks
Replace CPTs in Bayesian network
Simplify output query to a Bayesian network
Probability propagation in graphical independence networks, also known as Bayesian networks or probabilistic expert systems. Documentation of the package is provided in vignettes included in the package and in the paper by Højsgaard (2012, <doi:10.18637/jss.v046.i10>). See 'citation("gRain")' for details.