Projects per year
Recent developments in structural equation modeling have produced several methods that can usually distinguish cause from effect in the two-variable case. For that purpose, how- ever, one has to impose substantial structural constraints or smoothness assumptions on the functional causal mod- els. In this paper, we consider the problem of determining the causal direction from a related but different point of view, and propose a new framework for causal direction de- termination. We show that it is possible to perform causal inference based on the condition that the cause is “exoge- nous” for the parameters involved in the generating pro- cess from the cause to the effect. In this way, we avoid the structural constraints required by the SEM-based ap- proaches. In particular, we exploit nonparametric methods to estimate marginal and conditional distributions, and pro- pose a bootstrap-based approach to test for the exogeneity condition; the testing results indicate the causal direction between two variables. The proposed method is validated on both synthetic and real data.
|Title of host publication||Proceedings of the 15th conference on Theoretical Aspects of Rationality and Knowledge|
|Number of pages||11|
|Publication status||Published - 22 Apr 2015|
|Event||Fifteenth conference on Theoretical Aspects of Rationality and Knowledge - Carnegie Mellon University, Pittsburgh, United States|
Duration: 4 Jun 2015 → 6 Jun 2015
|Conference||Fifteenth conference on Theoretical Aspects of Rationality and Knowledge|
|Abbreviated title||TARK 2015|
|Period||4/06/15 → 6/06/15|
|Other||TARK 2015 took place at the Carnegie Mellon University, Pittsburgh, USA during June 4--6, 2015. |
The mission of the TARK conferences is to bring together researchers from a wide variety of fields, including Artificial Intelligence, Cryptography, Distributed Computing, Economics and Game Theory, Linguistics, Philosophy, and Psychology, in order to further our understanding of interdisciplinary issues involving reasoning about rationality and knowledge.
- Causal discovery
- causal direction
- statistical independence