| Causal Inference by Surrogate Experiments: z-Identifiability |
Jun 2012 |
9 pages |
| Authors:
Elias Bareinboim; Judea Pearl; CALIFORNIA UNIV LOS ANGELES COGNITIVE SYSTEMS LAB
|
 | We address the problem of estimating the effect of intervening on a set of variables X from experiments on a different set, Z, that is more accessible to manipulation. This problem, which we call z-identifiability reduces to ordinary identifiability when Z = phi and like the latter, can be given syntactic characterization using the do-calculus [Pearl, 1995; 2000]. We provide a graphical necessary and sufficient condition for z- identifiability for ... |
|
| Controlling Selection Bias in Causal Inference |
Feb 2012 |
16 pages |
| Authors:
Elias Bareinboim; Judea Pearl; CALIFORNIA UNIV LOS ANGELES COGNITIVE SYSTEMS LAB
|
| Selection bias, caused by preferential exclusion of samples from the data, is a major obstacle to valid causal and statistical inferences; it cannot be removed by randomized experiments and can hardly be detected in either experimental or observational studies. This paper highlights several graphical and algebraic methods capable of mitigating and sometimes eliminating this bias. These non-parametric methods generalize previously reported results, and identify the type of knowledge that is ... |
|
| Dynamic Networks Techniques for Autonomous Planning and Control. Probabilistic Counterfactuals |
09 MAY 97 |
161 pages |
| Authors:
Judea Pearl; CALIFORNIA UNIV LOS ANGELES COGNITIVE SYSTEMS LAB
|
| We have reformulated Bayesian networks as carriers of causal information. The result is a more natural understanding of what the networks stand for, what judgments are required in constructing the network and, most importantly, how actions and plans are to be handled within the framework of standard probability theory. Starting with functional description of physical mechanisms, we were able to derive the standard probabilistic properties of Bayesian networks and to ... |
|
| Counterfactuals and Policy Analysis in Structural Models |
JUN 95 |
9 pages |
| Authors:
Alexander A. Balke; Judea Pearl; CALIFORNIA UNIV LOS ANGELES COGNITIVE SYSTEMS LAB
|
| Evaluation of counterfactual queries (e.g., 'If A were true, would C have been true?') is important to fault diagnosis, planning, determination of liability, and policy analysis. We present a method for evaluating counter- factuals when the underlying causal model is represented by structural models a nonlinear generalization of the simultaneous equations models commonly used in econometrics and social sciences. This new method provides a coherent means for evaluating policies involving ... |
|
| Dynamic Constraints Networks |
31 OCT 89 |
4 pages |
| Authors:
Judea Pearl; CALIFORNIA UNIV LOS ANGELES COGNITIVE SYSTEMS LAB
|
| The objective of this effort was to develop a comprehensive and efficient model of dynamic constraint networks. The current available systems are either too complicated to understand of quite limited. The are not based on well understood theories. Their capabilities and boundaries are not formally assessed. This prevents comparison of different approaches which is essential in a process of developing and improving a model. A theory based on static approach ... |
|
| Goal-Directed Decision Structuring Systems |
31 AUG 1981 |
|
| Authors:
Judea Pearl; Robert Fiske; Jin Kim; CALIFORNIA UNIV LOS ANGELES COGNITIVE SYSTEMS LAB
|
 | The report summarizes the development and evaluation of computerized decision structuring systems based on a new representational structure which offers several advantages over the traditional decision-tree representation. The design and operating characteristics of GODDESS (A Goal-Directed Decision Structuring System) and several environment simulators used for evaluating decision aiding tools are briefly outlined. The main body of the report focuses on an experimental evaluation of the effectiveness of two structuring procedures: ... |
|
| Progress Toward a Goal-Directed Decision Support System. |
31 OCT 1979 |
|
| Authors:
Joseph Saleh ; Jin Kim ; Antonio Leal ; Judea Pearl; CALIFORNIA UNIV LOS ANGELES COGNITIVE SYSTEMS LAB
|
| This report describes a preliminary operational version of a computerized, domain-independent, decision-support system which is based on a novel, goal-directed structure for representing decision problems. The structure allows the user to state relations among aspects, effects, conditions, and goals, in addition to actions and states which are the basic components of the traditional decision-tree approach. The program interacts with the user in a stylized English-like dialogue, starting with the stated ... |
|
Reports by Corporate Author
