Token causation by probabilistic active paths

Twardy, Charles R. and Korb, Kevin B. and Oppy, Graham and Handfield, Toby (2005) Token causation by probabilistic active paths.

Full text available as:
PDF - Requires a viewer, such as Adobe Acrobat Reader or other PDF viewer.
Postscript (Zipped postscript file) - Requires a viewer, such as GhostView - GSView

Abstract

We present a probabilistic extension to active path analyses of token causation (Halpern & Pearl 2001, forthcoming; Hitchcock 2001). The extension uses the generalized notion of intervention presented in (Korb et al. 2004): we allow an intervention to set any probability distribution over the intervention variables, not just a single value. The resulting account can handle a wide range of examples. We do not claim the account is complete --- only that it fills an obvious gap in previous active-path approaches. It still succumbs to recent counterexamples by Hiddleston (2005), because it does not explicitly consider causal processes. We claim three benefits: a detailed comparison of three active-path approaches, a probabilistic extension for each, and an algorithmic formulation.

Keywords:Causal models, token causality, probabilistic causation, Bayesian networks
Subjects:Specific Sciences: Probability/Statistics
Specific Sciences: Computer Science: Artificial Intelligence
General Issues: Causation
ID Code:2146
Deposited By:Twardy, Charles R.
Deposited On:13 January 2005
Additional Information:Submitted to BJPS