The Graphical Identification for Total Effects by using Surrogate Variables
Manabu Kuroki, Zhihong Cai, Hiroki Motogaito
Consider the case where cause-effect relationships between variables can be described as a directed acyclic graph and the corresponding linear structural equation model. This paper provides graphical identifiability criteria for total effects by using surrogate variables in the case where it is difficult to observe a treatment/response variable. The results enable us to judge from graph structure whether a total effect can be identified through the observation of surrogate variables.
PDF Link: /papers/05/p340-kuroki.pdf
AUTHOR = "Manabu Kuroki
and Zhihong Cai and Hiroki Motogaito",
TITLE = "The Graphical Identification for Total Effects by using Surrogate Variables",
BOOKTITLE = "Proceedings of the Twenty-First Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-05)",
PUBLISHER = "AUAI Press",
ADDRESS = "Arlington, Virginia",
YEAR = "2005",
PAGES = "340--345"