query.cibn: Inference in a causal independence Bayesian network

In alessandromagrini/cibn: Causal Independence Bayesian Networks

Description

Perform exact inference in a causal independence Bayesian network through the joint tree algorithm (interface to the gRain package)

Usage

query.cibn(x, target=NULL, evidence=NULL, type="marginal")

Arguments

x	An object of class cibn.
target	The name of the target variable. If NULL (the default), all the variables in the Bayesian network will be set as targets.
evidence	A named list with each component indicating the evidence on a specific variable in the form of a vector of state names. See the examples below.
type	A character string indicating the type of inference: "marginal", "joint" or "conditional". Default is "marginal".

Details

This function is an interface to function querygrain in the gRain package.

Value

A list with one component for each variable in the Bayesian network, indicating its probability distribution given the evidence.

References

S. L. Lauritzen and D. J. Spiegelhalter (1988). Local computations with probabilities on graphical structures and their application to expert systems. Journal of the Royal Statistical Society, Series B (Methodological), 50(2): 157-224. DOI: 10.1023/A:1008935617754.

See Also

new.cibn; sample.cibn.

Examples

data(bankrisk_code)
bankrisk_bn <- new.cibn(bankrisk_code)
#
getStates(bankrisk_bn)  ## see the sample spaces
#
query.cibn(bankrisk_bn, target="Risk", evidence=list(Age="31_50",Portf="mixed"))
query.cibn(bankrisk_bn, target="Risk", evidence=list(Age="31_50",Portf="money_market"))
query.cibn(bankrisk_bn, target="Risk", evidence=list(Age="31_50",Portf="stock_market"))

alessandromagrini/cibn documentation built on Feb. 7, 2022, 10:55 p.m.