|
|
On the Testability of Causal Models with Latent and Instrumental Variables
Judea Pearl
Abstract:
Certain causal models involving unmeasured variables induce no independence constraints among the observed variables but imply, nevertheless, inequality contraints on the observed distribution. This paper derives a general formula for such instrumental variables, that is, exogenous variables that directly affect some variables but not all. With the help of this formula, it is possible to test whether a model involving instrumental variables may account for the data, or, conversely, whether a given variables can be deemed instrumental.
Keywords: Causal modeling, insrumental variables, structural models, graphical models.
Pages: 435-443
PS Link:
PDF Link: /papers/95/p435-pearl.pdf
BibTex:
@INPROCEEDINGS{Pearl95,
AUTHOR = "Judea Pearl
",
TITLE = "On the Testability of Causal Models with Latent and Instrumental Variables",
BOOKTITLE = "Proceedings of the Eleventh Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-95)",
PUBLISHER = "Morgan Kaufmann",
ADDRESS = "San Francisco, CA",
YEAR = "1995",
PAGES = "435--443"
}
|
|