Let G be a graph with the following edge types: o-o, o-> or <->, and let x be a vertex in the graph. Then this function computes Possible-D-SEP(x,G), which is defined as follows:

v is in Possible-D-SEP(x,G) iff there is a path p between x and v in G such that for every subpath <s,t,u> of p, t is a collider on this subpath or <s,t,u> is a triangle in G.

See Spirtes et al (2000) or Definition 3.3 of Colombo et al (2012).

1 |

`x` |
(integer) position of vertex |

`amat` |
Adjacency matrix of type amat.pag. |

`verbose` |
Logical, asking for details on output |

Vector of column positions indicating the nodes in Possible-D-SEP of x.

Markus Kalisch (kalisch@stat.math.ethz.ch)

P. Spirtes, C. Glymour and R. Scheines (2000).
*Causation, Prediction, and Search*, 2nd edition, The MIT Press.

D. Colombo, M.H. Maathuis, M. Kalisch, T.S. Richardson (2012).
Learning high-dimensional directed acyclic graphs with latent and
selection variables.
*Annals of Statistics* **40**, 294–321.

`fci`

and `pdsep`

which both use
this function.

Questions? Problems? Suggestions? Tweet to @rdrrHQ or email at ian@mutexlabs.com.

Please suggest features or report bugs with the GitHub issue tracker.

All documentation is copyright its authors; we didn't write any of that.