Probability theory is important because of its relevance for decision making, which also means: its relevance for the single case. The propensity theory of objective probability, which addresses the single case, is subject to two problems: Humphreys’ problem of inverse probabilities and the problem of the reference class. The paper solves both problems by restating the propensity theory using (an objectivist version of) Pearl’s approach to causality and probability, and by applying a decision-theoretic perspective. Contrary to a widely held view, (...) decision making on the basis of given propensities can proceed without a subjective-probability supplement to propensities. (shrink)

The first part of this paper shows that Qualitative Comparative Analysis (QCA)--also in its most recent forms as presented in Ragin (2000, 2008)--, does not correctly analyze data generated by causal chains, which, after all, are very common among causal processes in the social sciences. The incorrect modeling of data originating from chains essentially stems from QCA’s reliance on Quine-McCluskey optimization to eliminate redundancies from sufficient and necessary conditions. Baumgartner (2009a,b) has introduced a Boolean methodology, termed Coincidence Analysis (CNA), that (...) is related to QCA, yet, contrary to the latter, does not eliminate redundancies by means of Quine-McCluskey optimization. The second part of the paper applies CNA to chain-generated data. It will turn out that CNA successfully detects causal chains in small-N data. (shrink)

An actual cause of some token effect is itself a (distinct) token event (or fact, or state of affairs, …) that helped to bring about that effect. The notion of an actual cause is different from that of a potential cause – for example a pre-empted backup – which had the capacity to bring about the effect, but which wasn't in fact operative on the occasion in question. Sometimes actual causes are also distinguished from mere background conditions: as when we (...) judge that the struck match was a cause of the fire, while the presence of oxygen was merely part of the relevant background against which the struck match operated. Actual causation is also to be distinguished from type causation: actual causation holds between token events in a particular, concrete scenario; type causation, by contrast, holds between event kinds in scenario kinds. (shrink)

In a first part I present the results of the philosophy of scientific explanation with an attempt to apply them to the case of the theory of evolution. Then I observe that the requirements of modelization of phenomena with the help of inductive logic do not capture efficiently the pertinent factors and fail just as much to exclude those which end up being neutral as explanatory premises. I then query in the direction of confirmation theory, and show that probabilistic reasoning (...) does not possess the syntactic means of testing evolutionary hypotheses in a way that would rely on a valid mode of inference. In a second part, I try to show how biology has oscillated between two privileged modes of explanation, the first one being through form of which I suggest here that it has never been replaced and that it has known a forgotten vitality in the middle and latter part of the 19th Century, and the second one being through function here evaluated critically alongside that of tinkering. Finally, some limits are seen to hold against the pretence to epistemological exclusivism of those two outlooks on the biological object. (shrink)

The development of causal modelling since the 1950s has been accompanied by a number of controversies, the most striking of which concerns the Markov condition. Reichenbach's conjunctive forks did satisfy the Markov condition, while Salmon's interactive forks did not. Subsequently some experts in the field have argued that adequate causal models should always satisfy the Markov condition, while others have claimed that non-Markovian causal models are needed in some cases. This paper argues for the second position by considering the multi-causal (...) forks, which are widespread in contemporary medicine. (shrink)

Drawing substantive conclusions from linear causal models that perform acceptably on statistical tests is unreasonable if it is not known how alternatives fare on these same tests. We describe a computer program, TETRAD, that helps to search rapidly for plausible alternatives to a given causal structure. The program is based on principles from statistics, graph theory, philosophy of science, and artificial intelligence. We describe these principles, discuss how TETRAD employs them, and argue that these principles make TETRAD an effective tool. (...) Finally, we illustrate TETRAD's effectiveness by applying it to a multiple indicator model of Political and Industrial development. A pilot version of the TETRAD program is described in this paper. The current version is described in our forthcoming Discovering Causal Structure: Artificial Intelligence for Statistical Modeling. (shrink)

The starting point in the development of probabilistic analyses of token causation has usually been the naïve intuition that, in some relevant sense, a cause raises the probability of its effect. But there are well-known examples both of non-probability-raising causation and of probability-raising non-causation. Sophisticated extant probabilistic analyses treat many such cases correctly, but only at the cost of excluding the possibilities of direct non-probability-raising causation, failures of causal transitivity, action-at-a-distance, prevention, and causation by absence and omission. I show that (...) an examination of the structure of these problem cases suggests a different treatment, one which avoids the costs of extant probabilistic analyses. (shrink)

This paper presents a formalism that combines useful properties of both logic and probabilities. Like logic, the formalism admits qualitative sentences and provides symbolic machinery for deriving deductively closed beliefs and, like probability, it permits us to express if-then rules with different levels of firmness and to retract beliefs in response to changing observations. Rules are interpreted as order-of-magnitude approximations of conditional probabilities which impose constraints over the rankings of worlds. Inferences are supported by a unique priority ordering on rules (...) which is syntactically derived from the knowledge base. This ordering accounts for rule interactions, respects specificity considerations and facilitates the construction of coherent states of beliefs. Practical algorithms are developed and analyzed for testing consistency, computing rule ordering, and answering queries. Imprecise observations are incorporated using qualitative versions of Jeffrey's rule and Bayesian updating, with the result that coherent belief revision is embodied naturally and tractably. Finally, causal rules are interpreted as imposing Markovian conditions that further constrain world rankings to reflect the modularity of causal organizations. These constraints are shown to facilitate reasoning about causal projections, explanations, actions and change. (shrink)

Structural equations have become increasingly popular in recent years as tools for understanding causation. But standard structural equations approaches to causation face deep problems. The most philosophically interesting of these consists in their failure to incorporate a distinction between default states of an object or system, and deviations therefrom. Exploring this problem, and how to fix it, helps to illuminate the central role this distinction plays in our causal thinking.

This paper extends the account of actual causation offered by Halpern and Pearl [2005]. We show that this account yields the wrong judgment in certain classes of cases. We offer a revised definition that incorporates consideration of defaults, typicality, and normality. The revised definition takes actual causation to be both graded and comparative. We then apply our definition to a number of cases.

This paper presents an attempt to integrate theories of causal processes—of the kind developed by Wesley Salmon and Phil Dowe—into a theory of causal models using Bayesian networks. We suggest that arcs in causal models must correspond to possible causal processes. Moreover, we suggest that when processes are rendered physically impossible by what occurs on distinct paths, the original model must be restricted by removing the relevant arc. These two techniques suffice to explain cases of late preëmption and other cases (...) that have proved problematic for causal models. (shrink)

Hall [(2007), Philosophical Studies, 132, 109–136] offers a critique of structural equations accounts of actual causation, and then offers a new theory of his own. In this paper, I respond to Hall’s critique, and present some counterexamples to his new theory. These counterexamples are then diagnosed.

This paper argues against Papineau's claim that causal relations can be reduced to correlations and defends Cartwright's thesis that they can be nevertheless boot-strapped from them, given sufficiently rich causal background knowledge.

Causal modeling methods such as path analysis, used in the social and natural sciences, are also highly relevant to philosophical problems of probabilistic causation and statistical explanation. We show how these methods can be effectively used (1) to improve and extend Salmon's S-R basis for statistical explanation, and (2) to repair Cartwright's resolution of Simpson's paradox, clarifying the relationship between statistical and causal claims.

The aim of this paper is to investigate the ascription of probabilities in a causal model of an episode in the history of science. The aim of such a quantitative approach is to allow the implementation of the causal model in a computer, to run simulations. As an example, we look at the beginning of the science of magnetism, “explaining” — in a probabilistic way, in terms of a single causal model — why the field advanced in China but not (...) in Europe (the difference is due to different prior probabilities of certain cultural manifestations). Given the number of years between the occurrences of two causally connected advances X and Y, one proposes a criterion for stipulating the value pY/X of the conditional probability of an advance Y occurring, given X. Next, one must assume a specific form for the cumulative probability function pY/X(t), which we take to be the time integral of an exponential distribution function, as is done in physics of radioactive decay. Rules for calculating the cumulative functions for more than two events are mentioned, involving composition, disjunction and conjunction of causes. We also consider the problems involved in supposing that the appearance of events in time follows an exponential distribution, which are a consequence of the fact that a composition of causes does not follow an exponential distribution, but a “hypoexponential” one. We suggest that a gamma distribution function might more adequately represent the appearance of advances. (shrink)

Causal analysis in the social sciences takes advantage of a variety of methods and of a multi-fold source of information and evidence. This pluralistic methodology and source of information raises the question of whether we should accordingly have a pluralistic metaphysics and epistemology. This paper focuses on epistemology and argues that a pluralistic methodology and evidence don’t entail a pluralistic epistemology. It will be shown that causal models employ a single rationale of testing, based on the notion of variation. Further, (...) I shall argue that this monistic epistemology is also involved in alternative philosophical theories of causation. (shrink)

We propose a causal model theory to explain asymmetries in judgments of the intentionality of a foreseen side-effect that is either negative or positive (Knobe, 2003). The theory is implemented as a Bayesian network relating types of mental states, actions, and consequences that integrates previous hypotheses. It appeals to two inferential routes to judgment about the intentionality of someone else's action: bottom-up from action to desire and top-down from character and disposition. Support for the theory comes from three experiments that (...) test the prediction that bottom-up inference should occur only when the actor's primary objective is known. The model fits intentionality judgments reasonably well with no free parameters. (shrink)

Scientific and statistical inferences build heavily on explicit, parametric models, and often with good reasons. However, the limited scope of parametric models and the increasing complexity of the studied systems in modern science raise the risk of model misspecification. Therefore, I examine alternative, data-based inference techniques, such as bootstrap resampling. I argue that their neglect in the philosophical literature is unjustified: they suit some contexts of inquiry much better and use a more direct approach to scientific inference. Moreover, they make (...) more parsimonious assumptions and often replace theoretical understanding and knowledge about mechanisms by careful experimental design. Thus, it is worthwhile to study in detail how nonparametric models serve as inferential engines in science. (shrink)

Recently, a number of philosophers have advanced a surprising conclusion: people's judgments about whether an agent brought about an outcome intentionally are pervasively influenced by normative considerations. In this paper, we investigate the ‘Chairman case’, an influential case from this literature and disagree with this conclusion. Using a statistical method called structural path modeling, we show that people's attributions of intentional action to an agent are driven not by normative assessments, but rather by attributions of underlying values and characterological dispositions (...) to the agent. In a second study, we examined people's judgments about what they think drives asymmetric intuitions in the Chairman case and found that people are highly inaccurate in identifying which features of the case their intuitions track. In the final part of the paper, we discuss how the statistical methods used in this study can help philosophers with the critical features problem, the problem of figuring out which among the myriad features present in hypothetical cases are the critical ones that our intuitions are responsive to. We show how the methods used in this study have some advantages over both armchair methods used by traditional philosophers and survey methods used by experimental philosophers. (shrink)

One part of the true theory of actual causation is a set of conditions responsible for eliminating all of the non-causes of an effect that can be discerned at the level of counterfactual structure. I defend a proposal for this part of the theory.

Coherentism maintains that coherent beliefs are more likely to be true than incoherent beliefs, and that coherent evidence provides more confirmation of a hypothesis when the evidence is made coherent by the explanation provided by that hypothesis. Although probabilistic models of credence ought to be well-suited to justifying such claims, negative results from Bayesian epistemology have suggested otherwise. In this essay we argue that the connection between coherence and confirmation should be understood as a relation mediated by the causal relationships (...) among the evidence and a hypothesis, and we offer a framework for doing so by fitting together probabilistic models of coherence, confirmation, and causation. We show that the causal structure among the evidence and hypothesis is sometimes enough to determine whether the coherence of the evidence boosts confirmation of the hypothesis, makes no difference to it, or even reduces it. We also show that, ceteris paribus, it is not the coherence of the evidence that boosts confirmation, but rather the ratio of the coherence of the evidence to the coherence of the evidence conditional on a hypothesis. (shrink)