Instrumental variables in Gaussian directed acyclic graph models with an unobserved confounder
Elena Stanghellini · Environmetrics · 2004
Abstract We discuss the problem of identification of relevant parameters in a DAG model for Gaussian variables with one unobserved variable that acts as a counfounder. We first make explicit what we intend for identification and then discuss an example where a modified notion of instrumental variable renders a system with a confounder identifiable. Copyright © 2004 John Wiley & Sons, Ltd.