The Graphical Identification for Total Effects by Using Surrogate Variables
Abstract
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.
Cite
Text
Kuroki et al. "The Graphical Identification for Total Effects by Using Surrogate Variables." Conference on Uncertainty in Artificial Intelligence, 2005.Markdown
[Kuroki et al. "The Graphical Identification for Total Effects by Using Surrogate Variables." Conference on Uncertainty in Artificial Intelligence, 2005.](https://mlanthology.org/uai/2005/kuroki2005uai-graphical/)BibTeX
@inproceedings{kuroki2005uai-graphical,
title = {{The Graphical Identification for Total Effects by Using Surrogate Variables}},
author = {Kuroki, Manabu and Cai, Zhihong and Motogaito, Hiroki},
booktitle = {Conference on Uncertainty in Artificial Intelligence},
year = {2005},
pages = {340-345},
url = {https://mlanthology.org/uai/2005/kuroki2005uai-graphical/}
}