build_triplet_network: The simplest case of for testing conditional independence is...

In robertness/bninfo: Queries and information theoritic operations on Bayesian networks.

Description

The simplest case of for testing conditional independence is one of three variables – two to compare, and one variable upon which to condition the comparison. These function generates a Gaussian Bayesian network structure composed of three variable subnetworks of the form B <- C -> A.

Usage

build_triplet_network(m)

modify_triplet_cpd(reg_line, rho)

modify_triplet_cpds(net, rho)

Arguments

rho	the desired value of the correlation.
net	object of bn.fit, bn.fit.gnet
Number	of triplets. #' @param reg_line an element of the bn.fit.gnet class. This is treated here as a list element, since the class uses S3. The element is a regression line CPD, either of length 1 or 2.

robertness/bninfo documentation built on May 27, 2019, 10:32 a.m.