Probabilistic reasoning in intelligent systems: networks of plausible inference
Probabilistic reasoning in intelligent systems: networks of plausible inference
From Adams' conditionals to default expressions, causal conditionals, and counterfactuals
Probability and conditionals
The Art of Causal Conjecture
Default Reasoning: Causal and Conditional Theories
Default Reasoning: Causal and Conditional Theories
Counterfactuals and policy analysis in structural models
UAI'95 Proceedings of the Eleventh conference on Uncertainty in artificial intelligence
Testing identifiability of causal effects
UAI'95 Proceedings of the Eleventh conference on Uncertainty in artificial intelligence
A definition and graphical representation for causality
UAI'95 Proceedings of the Eleventh conference on Uncertainty in artificial intelligence
The ramification problem in temporal databases: an approach with conflicting constraints
Journal of Intelligent Information Systems
Hi-index | 0.00 |
The central aim of many empirical studies in the physical, behavioral, social, and biological sciences is the elucidation of cause-effect relationships among variables. It is through cause-effect relationships that we obtain a sense of a "deep understanding" of a given phenomenon, and it is through such relationships that we obtain a sense of being "in control," namely, that we are able to shape the course of events by deliberate actions or policies. It is for these two reasons, understanding and control, that causal thinking is so pervasive, popping up in everything from everyday activities to high-level decision-making: For example, every car owner wonders why an engine won't start; a cigarette smoker would like to know, given his/her specific characteristics, to what degree his/her health would be affected by refraining from further smoking; a policy maker would like to know to what degree anti-smoking advertising would reduce costs of health care; and so on. Although a plethora of data has been collected on cars and on smoking and health, the appropriate methodology for extracting answers to such questions from the data has been fiercely debated, partly because some fundamental questions of causality have not been given fully satisfactory answers.