The L-separation criterion for description of cs-independence models

Different conditional independence models have been proposed in literature; in this paper we consider models induced by conditional probabilities based on the definition of conditional cs-independence. These models need not comply with the symmetry property, so that they have not the graphoid structure. Hence, the well-known d-separation criterion for directed acyclic graphs may not be able to represent such independence models. Therefore, we introduce a new separation criterion called L-separation. We study its main properties and show how it allows to represent the above-mentioned independence models through directed acyclic graphs. (C) 2002 Elsevier Science Inc. All rights reserved.