Identifiability of intermediate variables on causal paths

Abstract

We discuss the discovery of causal mechanisms and identifiability of intermediate variables on a causal path. Different from variable selection, we try to distinguish intermediate variables on the causal path from other variables. It is also different from ordinary model selection approaches which do not concern the causal relationships and do not contain unobserved variables. We propose an approach for selecting a causal mechanism depicted by a directed acyclic graph (DAG) with an unobserved variable. We consider several causal networks, and discuss their identifiability by observed data. We show that causal mechanisms of linear structural equation models are not identifiable. Furthermore, we present that causal mechanisms of nonlinear models are identifiable, and we demonstrate the identifiability of causal mechanisms of quadratic equation models. Sensitivity analysis is conducted for the identifiability.

Keywords

Causal network / directed acyclic graph (DAG) / identifiability / intermediate variable / structural equation model

References

[1] He Y, Geng Z. Active learning of causal networks with intervention experiments and optimal designs. J Mach Learn Res, 2008, 9: 2523-2547

[2] Lauritzen S L. Discussion on causality. Scand J Stat, 2004, 31: 189-192

[3] Liu B H, Guo J H, Jing B Y. A note on minimal d-separation trees for structural learning. Artificial Intelligence, 2010, 174: 442-448

[4] Neyman J. On the application of probability theory to agricultural experiments: Essay on principles, Section 9. Ann Agric Sci, 1923 Translated in: Statist Sci, 1990, 5: 465–480

[5] Pearl J. Causality: Models, Reasoning, and Inference, 2009 2nd ed Cambridge: Cambridge University Press

[6] Rubin D B. Estimating causal effects of treatments in randomized and nonrandomized studies. J Educat Psychology, 1974, 66: 688-701

[7] Spirtes P, Glymour C, Scheines R. Causation, Prediction and Search, 1993, New York: Springer-Verlag

[8] Xie X, Geng Z, Zhao Q. Decomposition of structural learning about directed acyclic graphs. Artificial Intelligence, 2006, 170: 422-439