basiSet: Basis set of a DAG

In ggm: Graphical Markov Models with Mixed Graphs

Description

Finds a basis set for the conditional independencies implied by a directed acyclic graph, that is a minimal set of independencies that imply all the other ones.

Usage

basiSet(amat)

Arguments

amat	a square matrix with dimnames representing the adjacency matrix of a DAG.

Details

Given a DAG and a pair of non adjacent nodes (i,j) such that j has higher causal order than i, the set of independency statements i independent of j given the union of the parents of both i and j is a basis set (see Shipley, 2000). This basis set has the property to lead to independent test statistics.

Value

a list of vectors representing several conditional independence statements. Each vector contains the names of two non adjacent nodes followed by the names of nodes in the conditioning set (which may be empty).

Author(s)

Giovanni M. Marchetti

References

Shipley, B. (2000). A new inferential test for path models based on directed acyclic graphs. Structural Equation Modeling, 7(2), 206–218.

See Also

shipley.test, dSep, DAG

Examples

## See Shipley (2000), Figure 2, p. 213
A <- DAG(x5~ x3+x4, x3~ x2, x4~x2, x2~ x1)
basiSet(A)

Example output

Loading required package: igraph

Attaching package: 'igraph'

The following objects are masked from 'package:stats':

    decompose, spectrum

The following object is masked from 'package:base':

    union


Attaching package: 'ggm'

The following object is masked from 'package:igraph':

    pa

[[1]]
[1] "x1" "x4" "x2"

[[2]]
[1] "x1" "x3" "x2"

[[3]]
[1] "x1" "x5" "x4" "x3"

[[4]]
[1] "x2" "x5" "x1" "x4" "x3"

[[5]]
[1] "x4" "x3" "x2"

ggm documentation built on March 26, 2020, 7:49 p.m.