bnlearn (version 4.4.1)

lm integration: Produce lm objects from Bayesian networks

Description

Take a bn object or bn.fit object encoding a Gaussian network and refit all the local distributions using lm(). This makes it possible to use all the functions provided by R for lm objects (summary, anova, etc.) to investigate the network.

Usage

# S3 method for bn
as.lm(x, data, ...)
# S3 method for bn.fit
as.lm(x, data, ...)
# S3 method for bn.fit.gnode
as.lm(x, data, ...)

Arguments

x

an object of class bn, bn.fit or bn.fit.gnode.

data

a data frame containing the variables in the model.

…

additional arguments, currently ignored.

Value

If x is an object of class bn or bn.fit, as.lm() returns a list of lm objects, one for each node in x. If x is an object of class bn or bn.fit.gnode, as.lm() returns a single lm object.

Examples

# NOT RUN {
dag = hc(gaussian.test)
fitted = bn.fit(dag, gaussian.test)
as.lm(dag, gaussian.test)
as.lm(fitted, gaussian.test)
as.lm(fitted$F, gaussian.test)
# }