bnpa (version 0.3.0)

gera.pa: Generates a PA model

Description

This function receives a BN structure learned, the data set and some parameters and build a PA input model string. Then run the PA model using Structural Equation Model functions and export a PA graph and a PA model summary information.

Usage

gera.pa(bn.structure, data.to.work, pa.name, pa.imgname, bn.algorithm,
  bn.score.test, outcome.var)

Arguments

bn.structure

is a BN structure learned from data.

data.to.work

is a data frame containing the variables of the BN.

pa.name

is a variable to store the name of file to save PA parameters.

pa.imgname

is a variable to store the name of file to save PA graph.

bn.algorithm

is a list of algorithms to learn the BN structure.

bn.score.test

is a list of tests to be used during BN structure learning.

outcome.var

is the outcome variable.

References

Yves Rosseel (2012). lavaan: An R Package for Structural Equation Modeling. Journal of Statistical Software, 48(2),1-36.

Examples

# NOT RUN {
# Clean environment
closeAllConnections()
rm(list=ls())
# Set enviroment
# setwd("To your working directory")
# Load packages
library(bnpa)
# Load data sets from package
data(dataQualiN)
# Show first lines
head(dataQualiN)
# Learn BN structure
bn.structure <- bnlearn::hc(dataQualiN)
bnlearn::graphviz.plot(bn.structure)
# Set variables
pa.name<-"docPAHC"
pa.imgname<-"imgPAHC"
bn.algorithm<-"hc"
bn.score.test<-"aic-g"
outcome.var<-"D"
# Generates the PA model from bn structure
gera.pa(bn.structure, dataQualiN, pa.name, pa.imgname, bn.algorithm, bn.score.test, outcome.var)
# }