Results 1 
7 of
7
Assessing interactive causal influence
 Psychological Review
"... The discovery of conjunctive causes—factors that act in concert to produce or prevent an effect—has been explained by purely covariational theories. Such theories assume that concomitant variations in observable events directly license causal inferences, without postulating the existence of unobserv ..."
Abstract

Cited by 25 (6 self)
 Add to MetaCart
The discovery of conjunctive causes—factors that act in concert to produce or prevent an effect—has been explained by purely covariational theories. Such theories assume that concomitant variations in observable events directly license causal inferences, without postulating the existence of unobservable causal relations. This article discusses problems with these theories, proposes a causalpower theory that overcomes the problems, and reports empirical evidence favoring the new theory. Unlike earlier models, the new theory derives (a) the conditions under which covariation implies conjunctive causation and (b) functions relating observable events to unobservable conjunctive causal strength. This psychological theory, which concerns simple cases involving 2 binary candidate causes and a binary effect, raises questions about normative statistics for testing causal hypotheses regarding categorical data resulting from discrete variables. The preparation of this article was supported by National Science
Probabilities of Causation: Bounds and Identification
 Annals of Mathematics and Artificial Intelligence
, 2000
"... This paper deals with the problem of estimating the probability of causation, that is, the probability that one event was the real cause of another, in a given scenario. Starting from structuralsemantical definitions of the probabilities of necessary or sufficient causation (or both), we show h ..."
Abstract

Cited by 16 (10 self)
 Add to MetaCart
This paper deals with the problem of estimating the probability of causation, that is, the probability that one event was the real cause of another, in a given scenario. Starting from structuralsemantical definitions of the probabilities of necessary or sufficient causation (or both), we show how to bound these quantities from data obtained in experimental and observational studies, under general assumptions concerning the datagenerating process. In particular, we strengthen the results of Pearl (1999) by presenting sharp bounds based on combined experimental and nonexperimental data under no process assumptions, as well as under the mild assumptions of exogeneity (no confounding) and monotonicity (no prevention). These results delineate more precisely the basic assumptions that must be made before statistical measures such as the excessriskratio could be used for assessing attributional quantities such as the probability of causation. 1
Probabilities of causation: Three counterfactual interpretations and their identification
 SYNTHESE
, 1999
"... According to common judicial standard, judgment in favor of plaintiff should be made if and only if it is "more probable than not" that the defendant's action was the cause for the plaintiff's damage (or death). This paper provides formal semantics, based on structural models of counterfactuals, ..."
Abstract

Cited by 11 (5 self)
 Add to MetaCart
According to common judicial standard, judgment in favor of plaintiff should be made if and only if it is "more probable than not" that the defendant's action was the cause for the plaintiff's damage (or death). This paper provides formal semantics, based on structural models of counterfactuals, for the probability that event x was a necessary or sufficient cause (or both) of another event y. The paper then explicates conditions under which the probability of necessary (or sufficient) causation can be learned from statistical data, and shows how data from both experimental and nonexperimental studies can be combined to yield information that neither study alone can provide. Finally,weshow that necessity and sufficiency are two independent aspects of causation, and that both should be invoked in the construction of causal explanations for specific scenarios.
Probabilities of causation: Bounds and identi cation
 In Proceedings of the Sixteenth Conference on Uncertainty in Arti cial Intelligence
, 2000
"... This paper deals with the problem of estimating the probability that one event was a cause of another in a given scenario. Using structuralsemantical de nitions of the probabilities of necessary or su cient causation (or both), we show howto optimally bound these quantities from data obtained in ex ..."
Abstract

Cited by 6 (5 self)
 Add to MetaCart
This paper deals with the problem of estimating the probability that one event was a cause of another in a given scenario. Using structuralsemantical de nitions of the probabilities of necessary or su cient causation (or both), we show howto optimally bound these quantities from data obtained in experimental and observational studies, making minimal assumptions concerning the datagenerating process. In particular, we strengthen the results of Pearl (1999) by weakening the datageneration assumptions and deriving theoretically sharp bounds on the probabilities of causation. These results delineate precisely how empirical data can be used both in settling questions of attribution and in solving attributionrelated problems of decision making. 1
Populations at Risk: Addressing Health Effects Due to Complex Mixtures with a Focus on Respiratory Effects
"... Some individuals in the population may be sensitive or susceptible be to the effects of air pollutants. Such sensitivity may be to specific pollutants or classes of pollutants. However, sensitivity or susceptibility in some individuals can be to all irritants, but the semivity is luly to be respoesp ..."
Abstract
 Add to MetaCart
Some individuals in the population may be sensitive or susceptible be to the effects of air pollutants. Such sensitivity may be to specific pollutants or classes of pollutants. However, sensitivity or susceptibility in some individuals can be to all irritants, but the semivity is luly to be respoespecifi g or organpspef. The US. Clean Air Act s recognie that some individuals in the population are sensitive to air pollutants and indicates that such individuals need to be protected by air quality standards. It is usually difficult to determine the cause of sensitivity, though various biolgical have been studied. Biological age may be a factor, with the young being most sensitive and susceptible to being affected. An eammple is the heightened bronchial lability and responsiveness in the very young that appears to disappear with growth. Susceptibility may be innate (e.g., genetic) and/or induced by events/eqxosures. Frequendy, those with isn ilnesses are part of the sensitive population because they may often respond, sometimes hyperrespond, to a pollutant expore that may not affect most people. A tics aree nt examples of individuals who were useptibleto the dbie and, once inflicted, are susceptible to the effects of many ni ental and nonenvironmental agents. Usually only a fraction of the general population will respond with heightened rctioat lower doses. Such indhvidualsrequire specialevluation and attention in all exposureresponse studies and risk assesments Thus, thecnditons ddinn populations at risk and the methodologies to discover and study them can be reviewed.
Statistical Models for Genetic Susceptibility in Toxicological and Epidemiological Investigations
"... Models are presented for we in assessing genetic susceptibility to cancer (or other diseases) with animal or human data. Observations are assumed to be in the form of proportions, hence a binomial sampling distribution is considered. Generalized linear models are employed to model the response as a ..."
Abstract
 Add to MetaCart
Models are presented for we in assessing genetic susceptibility to cancer (or other diseases) with animal or human data. Observations are assumed to be in the form of proportions, hence a binomial sampling distribution is considered. Generalized linear models are employed to model the response as a function of the genetic component; these include logistic and complementary log forms. Susceptibility is measured via odds ratios of response, relative to a background genetic group. g ancestess and confidence intervals for these odds ratios are based onmaximum likelihod estimatesof the regression parameters. Additionalconideration is given to the problem ofgeneenvironment inteactosand to testing whether certain genetic identifiers/categories may be collapsed into a smaller set of categories. The collapsibility hypothesis provides an example of a mechanistic context wherein nonhierarchical models for the linear predictor can sometimes make sense.
Probabilities of Causation: Bounds and
, 2000
"... This paper deals with the problem of estimating the probability of causation, that is, the probability that one event was the real cause of another, in a given scenario. Starting from structuralsemantical de nitions of the probabilities of necessary or su cient causation (or both), we show how to b ..."
Abstract
 Add to MetaCart
This paper deals with the problem of estimating the probability of causation, that is, the probability that one event was the real cause of another, in a given scenario. Starting from structuralsemantical de nitions of the probabilities of necessary or su cient causation (or both), we show how to bound these quantities from data obtained in experimental and observational studies, under general assumptions concerning the datagenerating process. In particular, we strengthen the results of Pearl (1999) by presenting sharp bounds based on combined experimental and nonexperimental data under no process assumptions, as well as under the mild assumptions of exogeneity (no confounding) and monotonicity (no prevention). These results delineate more precisely the basic assumptions that must be made before statistical measures such as the excessriskratio could be used for assessing attributional quantities such as the probability of causation. 1