SMLG (Statistical Machine Learning Group) Discussion Forum

This study was based on the fourth and fifth KNHANES (2008–2012) which was conducted as a national health survey in Korea that used a stratified, multistage, clustered sampling method based on 2005 National Census data to randomly select a population-based sample across 500 national districts to represent the civilian, noninstitutionalized, South Korean population, and sample design and size were estimated properly so that annual survey results could represent the whole population in Korea.

raw dataset (modified for SPSS analysis)

the dataset for Banjo analysis (setting file, input file, and SPSS raw file)

Tables that summarize the data analyzed so far

The graph showing our Banjo results (19 variables)

Some r function to do Bayesian network analysis.

install.packages("bnlearn")
library(bnlearn)
data = read.table("data.txt", header = TRUE)
score(dag, data = marks, type = "loglik-g") -- get the score of the network
bnlearn::score(dag, data, type = "bge", iss = 5)

vstructs(dag) - v structure

graphviz.plot(dag2, highlight = hl2, layout = "fdp",
main = "dag2") --- plot the network

The following is some structure learning algorithm.
bn.gs = gs(data)
bn.iamb = iamb(data)
bn.iamb2 = iamb(data, test = "mc-cor")
bn.hc = hc(data)

Thank you and I'll try to run 'bnlearn'.

I attached the original raw SPSS dataset for dividing groups randomly using R.
I removed missing data for analyzing using Banjo or Bnlearn.
There are 18 variables and total n is 27837.

Best,
Duck Jin

The attachment is split dataset.

zgong001 wrote:The attachment is split dataset.

Could you post how you split the dataset, e.g., what program you used with what configuration?