Interaction Graphs for Multivariate Binary Data

We define a class of graphs that summarize in a compact visual way the interaction structure between binary multivariate characteristics. This allows studying the conditional dependency structure between the underlying stochastic variables at a finer scale than with classical probabilistic Graphical Models. A model selection strategy is derived based on an iterative optimization procedure and the consistency problem is discussed. We include the analysis of two data-sets to illustrate the proposed approach.

• Type: Journal
• Year: 2010
• Where: IBERAMIA
• Authors: Johan Van Horentonioeek, Jesús Emeterio Navarro-Barrientos
• Keywords: Artificial Intelligence, Binary Multivariate Characteristics, Compact Visual Way, Conditional Dependency Structure, IBERAMIA 2010