Causal Reasoning, Misc

Within Non-monotonic Reasoning, numerous principles of causal reasoning have been proposed. Many of these principles have been viewed as desirable in formalisms that reason with causality, and have been widely adopted throughout the literature. We provide a critique of these principles, evaluate their suitability for characterising and formulating causal non-monotonic reasoning, and find that most are unsuitable. Further, we discuss a new approach to causal non-monotonic reasoning motivated by how humans typically reason with causality.

The causal representative theory of perception dominated theory of knowledge for hundreds of years after it was put on the map by Descartes and Locke. It is now almost extinct. How could this happen? The theory collapsed because it could not explain how we acquire knowledge of the external world, since it presupposes a causally organized system of external objects producing sensations in us. This presupposition, however, is generally recognized as true, so that the pattern of causal inference at the (...) heart of the theory is surely justified. The theory cannot explain how we originally acquire our knowledge of the external world, but it is entitled on a second pass to correct our empirical beliefs, where necessary. This includes replacing our naive picture of the physical world with a more sophisticated scientific conception, which downgrades secondary qualities. This was, indeed, the main reason why it was originally introduced by Descartes and Locke, and has been the source of its attraction over the years. (shrink)

Temporal binding refers to a phenomenon whereby the time interval between a cause and its effect is perceived as shorter than the same interval separating two unrelated events. We examined the developmental profile of this phenomenon by comparing the performance of groups of children (aged 6-7-, 7-8-, and 9-10- years) and adults on a novel interval estimation task. In Experiment 1, participants made judgments about the time interval between i) their button press and a rocket launch, and ii) a non-causal (...) predictive signal and rocket launch. In Experiment 2, an additional causal condition was included in which participants made judgments about the interval between an experimenter’s button press and the launch of a rocket. Temporal binding was demonstrated consistently and did not change in magnitude with age: estimates of delay were shorter in causal contexts for both adults and children. Additionally, the magnitude of the binding effect was greater when participants themselves were the cause of an outcome compared to when they were mere spectators. This suggests that although causality underlies the binding effect, intentional action may modulate its magnitude. Again, this was true of both adults and children. Taken together, these results are the first to suggest that the binding effect is present and developmentally constant from childhood into adulthood. (shrink)

In temporal binding, the temporal interval between one event and another, occurring some time later, is subjectively compressed. We discuss two ways in which temporal binding has been conceptualized. In studies showing temporal binding between a voluntary action and its causal consequences, such binding is typically interpreted as providing a measure of an implicit or pre-reflective “sense of agency”. However, temporal binding has also been observed in contexts not involving voluntary action, but only the passive observation of a cause-effect sequence. (...) In those contexts, it has been interpreted as a top-down effect on perception reflecting a belief in causality. These two views need not be in conflict with one another, if one thinks of them as concerning two separate mechanisms through which temporal binding can occur. In this paper, we explore an alternative possibility: that there is a unitary way of explaining temporal binding both within and outside the context of voluntary action as a top-down effect on perception reflecting a belief in causality. Any such explanation needs to account for ways in which agency, and factors connected with agency, have been shown to affect the strength of temporal binding. We show that principles of causal inference and causal selection already familiar from the literature on causal learning have the potential to explain why the strength of people’s causal beliefs can be affected by the extent to which they are themselves actively involved in bringing about events, thus in turn affecting binding. (shrink)

An intervention may have an effect on units other than those to which it was administered. This phenomenon is called interference and it usually goes unmodeled. In this paper, we propose to combine Lauritzen-Wermuth-Frydenberg and Andersson-Madigan-Perlman chain graphs to create a new class of causal models that can represent both interference and non-interference relationships for Gaussian distributions. Specifically, we define the new class of models, introduce global and local and pairwise Markov properties for them, and prove their equivalence. We also (...) propose an algorithm for maximum likelihood parameter estimation for the new models, and report experimental results. Finally, we show how to compute the effects of interventions in the new models. (shrink)

People’s causal judgments are susceptible to the action effect, whereby they judge actions to be more causal than inactions. We offer a new explanation for this effect, the counterfactual explanation: people judge actions to be more causal than inactions because they are more inclined to consider the counterfactual alternatives to actions than to consider counterfactual alternatives to inactions. Experiment 1a conceptually replicates the original action effect for causal judgments. Experiment 1b confirms a novel prediction of the new explanation, the reverse (...) action effect, in which people judge inactions to be more causal than actions in overdetermination cases. Experiment 2 directly compares the two effects in joint-causation and overdetermination scenarios and conceptually replicates them with new scenarios. Taken together, these studies provide support for the new counterfactual explanation for the action effect in causal judgment. (shrink)

During the first half of the 20th century, many philosophers of memory opposed the postulation of memory traces based on the claim that a satisfactory account of remembering need not include references to causal processes involved in recollection. However, in 1966, an influential paper by Martin and Deutscher showed that causal claims are indeed necessary for a proper account of remembering. This, however, did not settle the issue, as in 1977 Malcolm argued that even if one were to buy Martin (...) and Deutscher’s argument for causal claims, we still don’t need to postulate the existence of memory traces. This paper reconstructs the dialectic between realists and anti-realists about memory traces, suggesting that ultimately realists’ arguments amount to inferences to the best explanation. I then argue that Malcolm’s anti-realist strategy consists in the suggestion that causal explanations that do not invoke memory traces are at least as good as those that do. But then, contra Malcolm, I argue that there are a large number of memory phenomena for which explanations that do not postulate the existence of memory traces are definitively worse than explanations that do postulate them. Next, I offer a causal model based on an interventionist framework to illustrate when memory traces can help to explain memory phenomena and proceed to substantiate the model with details coming from extant findings in the neuroscience of memory. (shrink)

According to the traditional view, the following incompatibility holds true: in reasoning, either there is warrant (certainty) or there is novelty. If there is warrant, there is not novelty: that would be the case of deductive reasoning. If there is novelty, there is not warrant: that would be the case of inductive reasoning. Causal reasoning would belong to the second group because there is novelty and, therefore, there is not warrant in it. I argue that this is false: reasoning may (...) have novelty and, nevertheless, be a deductive one. That is precisely what happens in (some) causal reasoning. And I will develop the following line of argumentation: one thing is to warrant that some state of affairs exists and other thing is to warrant that warrant. So we may have correct deductive reasoning without having certainty of that correction, like in some cases of causal reasoning. (shrink)

Classical models of decision making deal fairly well with uncertainty, where settings are well-structured in terms of goals, alternatives, and consequences. Conversely, the typical ill-structured nature of strategy choices remains a challenge for extant models. Such cases can hardly build on the past, and their novelty makes the prediction of consequences a very difficult and poorly robust task. The weakness of the classical expected utility model in representing such problems has not been adequately solved by recent extensions. In this paper (...) we offer an explanatory coherence model for decision making in ill-structured problems. We model alternatives as sets of concurrent causal explanations of reality that act as justifications for action. According to these premises, choice is based on an evaluation of the internal coherence and the consistency of competing explanations of the available evidence. This model is psychologically grounded on causal inference and builds on the connectionist tradition of explanatory coherence. To illustrate the model, we consider the decision of investing in a new technology and we discuss how changes in the structure of alternatives may impact on the solution. We show how the final choice depends on collecting the relevant evidence, making the suitable hypotheses, and drawing the consistent causal explanations linking the two. (shrink)

Philosophical discussions have critically analysed the methodological pitfalls and epistemological implications of evidence assessment in medicine, however they have mainly focused on evidence of treatment efficacy. Most of this work is devoted to statistical methods of causal inference with a special attention to the privileged role assigned to randomized controlled trials in evidence based medicine. Regardless of whether the RCT’s privilege holds for efficacy assessment, it is nevertheless important to make a distinction between causal inference of intended and unintended effects, (...) in that the unknowns at stake are heterogonous in the two contexts. However, although “lower level” evidence is increasingly acknowledged to be a valid source of information contributory to assessing the risk profile of medications on theoretical or empirical grounds, current practices have difficulty in assigning a precise epistemic status to this kind of evidence because they are more or less implicitly parasitic on the methods developed to test drug efficacy. My thesis is that “lower level” evidence is justified on distinct grounds and at different conditions depending on the different epistemologies which one wishes to endorse, in that each impose different constraints on the methods we adopt to collect and evaluate evidence; such constraints ought to be understood to be different in the case of evidence for risk versus benefit assessment for a series of reasons which I will illustrate on the basis of the recent debate on the causal association between acetaminophen and asthma. (shrink)

Epidemiological methods, which combine population thinking and group comparisons, can primarily identify causes of disease in populations. There is therefore a tension between our intuitive notion of a cause, which we want to be deterministic and invariant at the individual level, and the epidemiological notion of causes, which are invariant only at the population level. Epidemiologists have given heretofore a pragmatic solution to this tension. Causal inference in epidemiology consists in checking the logical coherence of a causality statement and determining (...) whether what has been found grossly contradicts what we think we already know: how strong is the association? Is there a dose-response relationship? Does the cause precede the effect? Is the effect biologically plausible? Etc. This approach to causal inference can be traced back to the English philosophers David Hume and John Stuart Mill. On the other hand, the mode of establishing causality, devised by Jakob Henle and Robert Koch, which has been fruitful in bacteriology, requires that in every instance the effect invariably follows the cause (e.g., inoculation of Koch bacillus and tuberculosis). This is incompatible with epidemiological causality which has to deal with probabilistic effects (e.g., smoking and lung cancer), and is therefore invariant only for the population. (shrink)

Strand and Parkkinen criticize our dispositional account of causation in evidence‐based medicine for failing to provide a proper epistemology of causal knowledge. In particular, they claim that we do not explain how causal inferences should be drawn. In response, we point out that dispositionalism does indeed have an account of the epistemology of causation, including counterfactual dependence, intervention, prediction and clinical decision. Furthermore, we argue that this is an epistemology that fits better with the known fallibility of even our best‐informed (...) predictions. Predictions are made on the basis that causes dispose or tend towards their effects, rather than guarantee them. The ontology of causation remains a valuable study for, among other reasons, it tells us that powers do not always combine additively. This counts against the monocausality that is tested by randomized controlled trials. (shrink)

Medicine is the science and art of preventing, alleviating, or curing disease. Through diagnosis the physician identifies and names disease. While the concepts of disease and diagnosis are pivotal for medical science, philosophical ambiguities in both concepts persist and have great import for contemporary nosology. Unified concepts of disease have been built either on emphasis of exogenous causes of disease —xenochthonous models, or on emphasis of endogenous causes of diseases—autochthonous models. The choice between the two models is more than academic, (...) since the derivation of diagnostic algorithms from the two models can be shown to differ. (shrink)

Fundamental physics makes no clear use of causal notions; it uses laws that operate in relevant respects in both temporal directions and that relate whole systems across times. But by relating causation to evidence, we can explain how causation fits in to a physical picture of the world and explain its temporal asymmetry. This paper takes up a deliberative approach to causation, according to which causal relations correspond to the evidential relations we need when we decide on one thing in (...) order to achieve another. Tamsin's taking her umbrella is a cause of her staying dry, for example, if and only if her deciding to take her umbrella for the sake of staying dry is adequate grounds for believing she'll stay dry. This correspondence explains why causation matters: knowledge of causal structure helps us make decisions that are evidence of outcomes we seek. The account also explains why we can control the future and not the past, and why causes come before their effects. When agents properly deliberate, their decisions can never count as evidence for any outcomes they may seek in the past. From this it follows that causal relations don't run backwards. This deliberative asymmetry is itself traced back to asymmetries of evidence and entropy, providing a new way of deriving causal asymmetry from temporally symmetric laws. (shrink)

Causation has always been a philosophically controversial subject matter. While David Hume’s empiricist account of causation has been the dominant influence in analytic philosophy and science during modern times, a minority view has instead connected causation essentially to agency and manipulation. A related approach has for the first time gained widespread popularity in recent years, due to new powerful theories of causal inference in science that are based in a technical notion of intervention, and James Woodward’s closely connected interventionist theory (...) of causation in philosophy. This monograph assesses five manipulationist or interventionist theories of causation, viewed as theories that purport to tell us what causation is by providing us with the meaning of causal claims. It is shown that they cannot do this, as the conditions on causation that they impose are too weak, mainly due to ineliminable circularities in their definitions of causal terms. It is then argued that a subset of Woodward’s theory can nevertheless contribute crucially to an explanation of the unique role that manipulation has in our acquisition of causal knowledge. This explanation differs from the common regularist explanation of the epistemic utility of manipulation and experiment, and it is taken to confirm several important manipulationist intuitions. However, the success of the explanation depends on interventionism not itself being understood as a theory of causation, but as a theory of intervention. (shrink)

People more frequently select norm-violating factors, relative to norm- conforming ones, as the cause of some outcome. Until recently, this abnormal-selection effect has been studied using only retrospective vignette-based paradigms. In within-participants designs, we use a novel set of videos to investigate this effect for prospective causal judgments—i.e., judgments about the cause of some future outcome. Three experiments show that people more frequently select norm-violating factors, relative to norm-conforming ones, as the cause of some future outcome. We discuss these results (...) in relation to recent efforts to model causal judgment. (shrink)

This paper has two main parts. In the first part, we motivate a kind of indeterminate, suppositional credences by discussing the prospect for a subjective interpretation of a causal Bayesian network, an important tool for causal reasoning in artificial intelligence. A CBN consists of a causal graph and a collection of interventional probabilities. The subjective interpretation in question would take the causal graph in a CBN to represent the causal structure that is believed by an agent, and interventional probabilities in (...) a CBN to represent suppositional credences. We review a difficulty noted in the literature with such an interpretation, and suggest that a natural way to address the challenge is to go for a generalization of CBN that allows indeterminate credences. In the second part, we develop a decision-theoretic foundation for such indeterminate suppositional credences, by generalizing a theory of coherent choice functions to accommodate some form of act-state dependence. The upshot is a decision-theoretic framework that is not only rich enough to, so to speak, ground the probabilities in a subjectively interpreted causal network, but also interesting in its own right, in that it accommodates both act-state dependence and imprecise probabilities. (shrink)

This article provides a conceptual account of causal understanding by connecting current psychological research on time and causality with philosophical debates on the causal asymmetry. I argue that causal relations are viewed as asymmetric because they are understood in temporal terms. I investigate evidence from causal learning and reasoning in both children and adults: causal perception, the temporal priority principle, and the use of temporal cues for causal inference. While this account does not suffice for correct inferences of causal structure, (...) I show it to serve as a preliminary understanding of causal concepts as asymmetric, that later incorporates other types of evidence. This approach supplies causal models with an asymmetric concept of causation that underlies hypotheses about causal structure, as I will illustrate from the framework of the knowledge-based causal induction model. I further argue for an integrating perspective, showing how the understanding of causes as preceding their effects underlies both psychological models and philosophical debates over time and the causal asymmetry, particularly regarding problem cases such as simultaneous causation or backwards causation, and the conceptual connection between causation and action. (shrink)

In this paper, I examine Cicero’s oft-neglected De Divinatione, a dialogue investigating the legitimacy of the practice of divination. First, I offer a novel analysis of the main arguments for divination given by Quintus, highlighting the fact that he employs two logically distinct argument forms. Next, I turn to the first of the main arguments against divination given by Marcus. Here I show, with the help of modern probabilistic tools, that Marcus’ skeptical response is far from the decisive, proto-naturalistic assault (...) on superstition that it is sometimes portrayed to be. Then, I offer an extended analysis of the second of the main arguments against divination given by Marcus. Inspired by Marcus’ second main argument, I formulate, explicate, and defend a substantive principle of scientific methodology that I call the “Ciceronian Causal-Nomological Requirement” (CCR). Roughly, this principle states that causal knowledge is essential for relying on correlations in predictive inference. Although I go on to argue that Marcus’ application of the CCR in his debate with Quintus is dialectically inadequate, I conclude that De Divinatione deserves its place in Cicero’s philosophical corpus, and that ultimately, its significance for the history and philosophy of science ought to be recognized. (shrink)

Although it has long been known that time is a cue to causation, recent work with adults has demonstrated that causality can also influence the experience of time. In causal reordering (Bechlivanidis & Lagnado, 2013, 2016) adults tend to report the causally consistent order of events, rather than the correct temporal order. However, the effect has yet to be demonstrated in children. Across four pre-registered experiments, 4- to 10-year-old children (N=813) and adults (N=178) watched a 3-object Michotte-style ‘pseudocollision’. While in (...) the canonical version of the clip object A collided with B, which then collided with object C (order: ABC), the pseudocollision involved the same spatial array of objects but featured object C moving before object B (order: ACB), with no collision between B and C. Participants were asked to judge the temporal order of events and whether object B collided with C. Across all age groups, participants were significantly more likely to judge that B collided with C in the 3-object pseudocollision than in a 2-object control clip (where clear causal direction was lacking), despite the spatiotemporal relations between B and C being identical in the two clips (Experiments 1—3). Collision judgements and temporal order judgements were not entirely consistent, with some participants—particularly in the younger age range—basing their temporal order judgements on spatial rather than temporal information (Experiment 4). We conclude that in both children and adults, rather than causal impressions being determined only by the basic spatial-temporal properties of object movement, schemata are used in a top-down manner when interpreting perceptual displays. (shrink)

The long-enduring coding metaphor is deemed problematic because it imbues correlational evidence with causal power. In neuroscience, most research is correlational or conditionally correlational; this research, in aggregate, informs causal inference. Rather than prescribing semantics used in correlational studies, it would be useful for neuroscientists to focus on a constructive syntax to guide principled causal inference.

In Causation, Prediction, and Search, we undertook a three part project. First, we characterized when causal models are indistinguishable by population conditional independence relations under several different assumptions relating causality to probability. Second, we proposed a number of algorithms that take sample data and optional background knowledge as input, and output a class of causal models compatible with the data and the background knowledge; the algorithms were accompanied by proofs of their correctness given assumptions that were clearly stated in CPS, (...) and that we will restate below. Finally, we offered a theory of how to predict the effects of interventions in causal structures, given only partial knowledge of causal structure. Freedman's objections are all directed against the causal inference algorithms we proposed. We do not have room here to discuss all of his criticisms, but we have answered his major points. With regard to the points we do not have room to discuss, the reader should be warned that Freedman is an unreliable interpreter of what we have written. For convenience, we have divided Freedman's objections into the following categories. 1.) Freedman questions some of the assumptions on which our correctness theorems are based. Some of his criticisms are based on covariance matrices that he constructed. None of the examples he constructed in sections 11.2, 11.3, or 12.3 are counterexamples to any theorem that we stated, nor are they even germane to the question of how probable are the assumptions we make. His examples only illustrate points discussed in detail in our book, in which we give similar examples. 2.) The most serious charge that Freedman makes is that the algorithms do not compute what we say they do. (shrink)

This paper responds to criticisms of my account of the role of proportionality and stability in causal reasoning. It reformulates the notion of proportionality in response to objections.

In Nozick’s rendition of the decision situation given in Newcomb’s Paradox dominance and the principle of maximum expected utility recommend different strategies. While evidential decision theory seems to be split over which principle to apply and how to interpret the principles in the first place, causal decision theory seems to go for the solution recommended by dominance. As a reply to the CDT proposal by Wolfgang Spohn, who opts for “one-boxing” by employing reflexive decision graphs, I will draw on the (...) framework of causal knowledge patterns, i.e., Bayes net causal models, augmented by non-causal knowledge, to finally arrive at “one-boxing” – more intuitively and more closely to what actually is in Nozick’s story. This proposal allows the careful re-examination of all relevant concepts in the original story and might cast new light on the following questions: How may causality in general be understood to allow causal inference from hybrid patterns encoding subjective knowledge? How can the notion of prediction be analyzed – philosophically and formally? And what’s the decision-maker’s conceptualization of the situation he will act upon? (shrink)

Amalgamating evidence from heterogeneous sources and across levels of inquiry is becoming increasingly important in many pure and applied sciences. This special issue provides a forum for researchers from diverse scientific and philosophical perspectives to discuss evidence amalgamation, its methodologies, its history, its pitfalls, and its potential. We situate the contributions therein within six themes from the broad literature on this subject: the variety-of-evidence thesis, the philosophy of meta-analysis, the role of robustness/sensitivity analysis for evidence amalgamation, its bearing on questions (...) of extrapolation and external validity of experiments, its connection with theory development, and its interface with causal inference, especially regarding causal theories of cancer. (shrink)

A central theme in western philosophy was to find formal methods that can reliably discover empirical relationships and their explanations from data assembled from experience. As a philosophical project, that ambition was abandoned in the 20th century and generally dismissed as impossible. It was replaced in philosophy by neo-Kantian efforts at reconstruction and justification, and in professional statistics by the more limited ambition to estimate a small number of parameters in pre-specified hypotheses. The influx of “big data” from climate science, (...) neuropsychology, biology, astronomy and elsewhere implicitly called for a revival of the grander philosophical ambition. Search algorithms are meeting that call, but they pose a problem: how are their accuracies to be assessed in domains where experimentation is limited or impossible? Increasingly, the answer is through simulation of data from models of the kind of process in the domain. In some cases, these innovations require rethinking how the accuracy and informativeness of inference methods can be assessed. Focusing on causal inference, we give an example from neuroscience, but to show that the model/simulation strategy is not confined to causal inference, we also consider two classification problems from astrophysics: identifying exoplanets and identifying dark matter concentrations. (shrink)

The E-value is defined as the minimum strength of association on the risk ratio scale that an unmeasured confounder would have to have with both the exposure and the outcome, conditional on the measured covariates, to explain away the observed exposure-outcome association. We have elsewhere proposed that the reporting of E-values for estimates and for the limit of the confidence interval closest to the null become routine whenever causal effects are of interest. A number of questions have arisen about the (...) use of E-value including questions concerning the interpretation of the relevant confounding association parameters, the nature of the transformation from the risk ratio scale to the E-value scale, inference for and using E-values, and the relation to Rosenbaum’s notion of design sensitivity. Here we bring these various questions together and provide responses that we hope will assist in the interpretation of E-values and will further encourage their use. (shrink)

Traditionally, social scientists perceived causality as regularity. As a consequence, qualitative comparative case study research was regarded as unsuitable for drawing causal inferences since a few cases cannot establish regularity. The dominant perception of causality has changed, however. Nowadays, social scientists define and identify causality through the counterfactual effect of a treatment. This brings causal inference in qualitative comparative research back on the agenda since comparative case studies can identify counterfactual treatment effects. We argue that the validity of causal inferences (...) from the comparative study of cases depends on the employed case-selection algorithm. We employ Monte Carlo techniques to demonstrate that different case-selection rules strongly differ in their ex ante reliability for making valid causal inferences and identify the most and the least reliable case selection rules. (shrink)

This paper provides empirical interpretation of the d o do operator when applied to non-manipulable variables such as race, obesity, or cholesterol level. We view d o do as an ideal intervention that provides valuable information on the effects of manipulable variables and is thus empirically testable. We draw parallels between this interpretation and ways of enabling machines to learn effects of untried actions from those tried. We end with the conclusion that researchers need not distinguish manipulable from non-manipulable variables; (...) both types are equally eligible to receive the d o do operator and to produce useful information for decision makers. (shrink)

A key issue in the analysis of traffic accidents is to quantify the effectiveness of a given evasive action taken by a driver to avoid crashing. Since 1977, the widely accepted definition for this effectiveness measure, which is called traffic conflict, has been “the risk of a collision if the driver movement remains unchanged.” Although the definition is expressed counterfactually, the full power of counterfactual analysis was not utilized. In this paper, we propose a counterfactual measure of traffic conflict called (...) Counterfactual Based Conflict. The CBC is interpreted as the probability that a driver avoided a crash actually by taking an evasive action in the counterfactual situation in which the crash would have occurred if he/she had not taken an evasive action and the crash would not have occurred if he/she had taken an evasive action. The CBC captures realistic aspects of the traffic situation, and lends itself to modern causal analysis. In addition, we provide some of identification conditions for the CBC. Furthermore, we formulate bounds on the CBC when the proposed identification conditions are violated. Finally, through an application of the CBC to the 100-Car Naturalistic Driving Study, we discuss the usefulness and limitations of the proposed measure. (shrink)

Despite the miraculous progress of science—it’s practitioners continue to run into mistakes, either discrediting research unduly or making leaps of causal inference where none are warranted. In this we isolate two of the reasons for such behavior involving the misplaced understanding of the role of mechanisms and mechanistic knowledge in the establishment of cause-effect relationships. We differentiate causal knowledge into causes, effects, mechanisms, cause-effect relationships, and causal stories. Failing to understand the role of mechanisms in this picture, including their absence (...) of knowledge or incorrect specification, leads to errors of wrongly excluding cause-effect relationships or wrongly inferring their existence. We highlight the primary of causality over mechanistic knowledge and causal stories in scientific reasoning. (shrink)

We consider ways of enabling systems to apply previously learned information to novel situations so as to minimize the need for retraining. We show that theoretical limitations exist on the amount of information that can be transported from previous learning, and that robustness to changing environments depends on a delicate balance between the relations to be learned and the causal structure of the underlying model. We demonstrate by examples how this robustness can be quantified.

Mann–Whitney-type causal effects are clinically relevant, easy to interpret, and readily applicable to a wide range of study settings. This article considers estimation of such effects when the outcome variable is a survival time subject to right censoring. We derive and discuss several methods: an outcome regression method based on a regression model for the survival outcome, an inverse probability weighting method based on models for treatment assignment and censoring, and two doubly robust methods that involve both types of models (...) and that remain valid under correct specification of the outcome model or the other two models. The methods are compared in a simulation study and applied to an observational study of hospitalized pneumonia. (shrink)

Mental causation is a predominantly theoretical topic rather than a topic studied in the laboratory. The purpose of this paper is to outline a general approach for studying mental causation by empirical means for philosophers and scientists interested in the topic. The aim is to outline how we can infer mental causation by empirical methods given an unknown solution to the mind-body problem. The approach is based on the principles of causal inference to find causal relations among observed variables used (...) in all branches of science. With these principles, it is possible to estimate the causal effects of mental events: Make an experimental manipulation of a mental event, control confounding variables, and estimate causal effects on the outcome. The caveat is that we cannot separate the causal effects of a mental event from the physical base of the mental event, independent of whether we assume mental events can be reduced to their physical base. A challenge to estimating causal effects of mental events is that measured physical variables, such as electrophysiological potentials from the brain, might reflect processes that are part of “higher-order” phenomena, such as mental events. This means that controlling “downwards” for confounding variables is challenging. It is, however, not impossible. It also means that inferring non-mental causes of action cannot be done by measuring only physical variables alone. Keeping the mind-body problem in mind when designing experiments, it is possible to infer mental causation. (shrink)

We report three experiments investigating whether people’s judgments about causal relationships are sensitive to the robustness or stability of such relationships across a range of background circumstances. In Experiment 1, we demonstrate that people are more willing to endorse causal and explanatory claims based on stable (as opposed to unstable) relationships, even when the overall causal strength of the relationship is held constant. In Experiment 2, we show that this effect is not driven by a causal generalization’s actual scope of (...) application. In Experiment 3, we offer evidence that stable causal relationships may be seen as better guides to action. Collectively, these experiments document a previously underappreciated factor that shapes people’s causal reasoning: the stability of the causal relationship. (shrink)

The structural interpretation of counterfactuals as formulated in Balke and Pearl [.

Prevented and preventable fractions have been widely used in medical science to evaluate the proportion of new diseases that can be averted by a protective exposure. However, most existing formulas used in practical situations cannot be interpreted as proportions without any further assumptions because they are obtained according to different target populations and may fall outside the range.

Linear structural equation models relate the components of a random vector using linear interdependencies and Gaussian noise. Each such model can be naturally associated with a mixed graph whose vertices correspond to the components of the random vector. The graph contains directed edges that represent the linear relationships between components, and bidirected edges that encode unobserved confounding. We study the problem of generic identifiability, that is, whether a generic choice of linear and confounding effects can be uniquely recovered from the (...) joint covariance matrix of the observed random vector. An existing combinatorial criterion for establishing generic identifiability is the half-trek criterion, which uses the existence of trek systems in the mixed graph to iteratively discover generically invertible linear equation systems in polynomial time. By focusing on edges one at a time, we establish new sufficient and new necessary conditions for generic identifiability of edge effects extending those of the HTC. In particular, we show how edge coefficients can be recovered as quotients of subdeterminants of the covariance matrix, which constitutes a determinantal generalization of formulas obtained when using instrumental variables for identification. While our results do not completely close the gap between existing sufficient and necessary conditions we find, empirically, that our results allow us to prove the generic identifiability of many more mixed graphs than the prior state-of-the-art. (shrink)

:1 In this paper, we study the effect of a time-varying exposure mediated by a time-varying intermediate variable. We consider general longitudinal settings, including survival outcomes. At a given time point, the exposure and mediator of interest are influenced by past covariates, mediators and exposures, and affect future covariates, mediators and exposures. Right censoring, if present, occurs in response to past history. To address the challenges in mediation analysis that are unique to these settings, we propose a formulation in terms (...) of random interventions based on conditional distributions for the mediator. This formulation, in particular, allows for well-defined natural direct and indirect effects in the survival setting, and natural decomposition of the standard total effect. Upon establishing identifiability and the corresponding statistical estimands, we derive the efficient influence curves and establish their robustness properties. Applying Targeted Maximum Likelihood Estimation, we use these efficient influence curves to construct multiply robust and efficient estimators. We also present an inverse probability weighted estimator and a nested non-targeted substitution estimator for these parameters. (shrink)