Probabilistic evaluation of counterfactual queries
AAAI '94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 1)
Causality: models, reasoning, and inference
Causality: models, reasoning, and inference
Hi-index | 0.00 |
Estimating individual probabilities of causation generally requires prior knowledge of causal mechanisms. For traffic accidents such knowledge is often available and supports the discipline of accident reconstruction. In this paper structural knowledge is combined with Bayesian network methods to calculate the probability of necessity due to speeding for each of a set of vehicle/pedestrian collisions. Gibbs sampling is used to carry out the computations.