pcalg (version 2.7-1)

gmD: Graphical Model Discrete 5-Dim Example Data

Description

This data set contains a matrix containing information on five discrete variables (levels are coded as numbers) and the corresonding DAG model.

Usage

data(gmD)

Format

A list of two components

x:

a data.frame with 5 columns X1 .. X5 each coding a discrete variable (aka factor) with interagesInt [1:10000, 1:5] 2 2 1 1 1 2 2 0 2 0 ...

g:

Formal class 'graphNEL' [package "graph"] with 6 slots .. ..@ nodes : chr [1:5] "1" "2" "3" "4" ... .. ..@ edgeL :List of 5 ........

where x is the data matrix and g is the DAG from which the data were generated.

Details

The data was generated using Tetrad in the following way. A random DAG on five nodes was generated; discrete variables were assigned to each node (with 3, 2, 3, 4 and 2 levels); then conditional probability tables corresponding to the structure of the generated DAG were constructed. Finally, 10000 samples were drawn using the conditional probability tables.

Examples

# NOT RUN {
data(gmD)
str(gmD, max=1)
if(require("Rgraphviz"))
  plot(gmD$ g, main = "gmD $ g --- the DAG of the gmD (10'000 x 5 discrete data)")
## >>>  1 --> 3 <-- 2 --> 4 --> 5
str(gmD$x)
## The number of unique values of each variable:
sapply(gmD$x, function(v) nlevels(as.factor(v)))
## X1 X2 X3 X4 X5
##  3  2  3  4  2
lapply(gmD$x, table) ## the (marginal) empirical distributions
## $X1
##    0    1    2
## 1933 3059 5008
##
## $X2
##    0    1
## 8008 1992
##
## $X3
## .....
# }

Run the code above in your browser using DataCamp Workspace