In medicine and the social sciences, researchers must frequently integrate the findings of many observational studies, which measure overlapping collections of variables. For instance, learning how to prevent obesity requires combining studies that investigate obesity and diet with others that investigate obesity and exercise. Recently developed causal discovery algorithms provide techniques for integrating many studies, but little is known about what can be learned from such algorithms. This article argues that there are causal facts that one could learn by conducting (...) a large study but which could not be learned by combining many smaller studies. Moreover, I characterize the frequency with which combining many studies increases underdetermination and exactly how much information is lost. 1 Introduction2 Causal Inference from Observational Data3 Piecemeal Causal Inference4 The Extent and Frequency of the Problem of Piecemeal Induction5 Conclusion. (shrink)

It is common to assume that the problem of induction arises only because of small sample sizes or unreliable data. In this paper, I argue that the piecemeal collection of data can also lead to underdetermination of theories by evidence, even if arbitrarily large amounts of completely reliable experimental and observational data are collected. Specifically, I focus on the construction of causal theories from the results of many studies (perhaps hundreds), including randomized controlled trials and observational studies, where the studies (...) focus on overlapping, but not identical, sets of variables. Two theorems reveal that, for any collection of variables V, there exist fundamentally different causal theories over V that cannot be distinguished unless all variables are simultaneously measured. Underdetermination can result from piecemeal measurement, regardless of the quantity and quality of the data. Moreover, I generalize these results to show that, a priori, it is impossible to choose a series of small (in terms of number of variables) observational studies that will be most informative with respect to the causal theory describing the variables under investigation. This final result suggests that scientific institutions may need to play a larger role in coordinating differing research programs during inquiry. (shrink)

In medicine and the social sciences, researchers often measure only a handful of variables simultaneously. The underlying assumption behind this methodology is that combining the results of dozens of smaller studies can, in principle, yield as much information as one large study, in which dozens of variables are measured simultaneously. Mayo-Wilson :864–874, 2011, Br J Philos Sci 65:213–249, 2013. https://doi.org/10.1093/bjps/axs030) shows that assumption is false when causal theories are inferred from observational data. This paper extends Mayo-Wilson’s results to cases in (...) which experimental data is available. I prove several new theorems that show that, as the number of variables under investigation grows, experiments do not improve, in the worst-case, one’s ability to identify the true causal model if one can measure only a few variables at a time. However, stronger statistical assumptions significantly aid causal discovery in piecemeal inquiry, even if such assumptions are unhelpful when all variables can be measured simultaneously. (shrink)

This book addresses key conceptual issues relating to the modern scientific and engineering use of computer simulations. It analyses a broad set of questions, from the nature of computer simulations to their epistemological power, including the many scientific, social and ethics implications of using computer simulations. The book is written in an easily accessible narrative, one that weaves together philosophical questions and scientific technicalities. It will thus appeal equally to all academic scientists, engineers, and researchers in industry interested in questions (...) related to the general practice of computer simulations. (shrink)

Causal inference in the empiricalsciences is based on counterfactuals. The mostcommon approach utilizes a statistical model ofpotential outcomes to estimate causal effectsof treatments. On the other hand, one leadingapproach to the study of causation inphilosophical logic has been the analysis ofcausation in terms of counterfactualconditionals. This paper discusses and connectsboth approaches to counterfactual causationfrom philosophy and statistics. Specifically, Ipresent the counterfactual account of causationin terms of Lewis's possible-world semantics,and reformulate the statistical potentialoutcome framework using counterfactualconditionals. This procedure highlights variousproperties and (...) mechanisms of the statisticalmodel. (shrink)

The essential precondition of implementing interventionist techniques of causal reasoning is that particular variables are identified as so-called intervention variables. While the pertinent literature standardly brackets the question how this can be accomplished in concrete contexts of causal discovery, the first part of this paper shows that the interventionist nature of variables cannot, in principle, be established based only on an interventionist notion of causation. The second part then demonstrates that standard observational methods that draw on Bayesian networks identify intervention (...) variables only if they also answer the questions that can be answered by interventionist techniques—which are thus rendered dispensable. The paper concludes by suggesting a way of identifying intervention variables that allows for exploiting the whole inferential potential of interventionist techniques. (shrink)

The present paper deals with the tools that can be used to represent causation and to reason about it and, specifically, with their diversity. It focuses on so-called “causal probabilities”—that is, probabilities of effects given one of their causes—and critically surveys a recent paper in which Joyce argues that the values of these probabilities do not depend on one’s conception of causation. I first establish a stronger independence claim: I show that the very definition of causal probabilities is independent of (...) one’s conception of causation. Second, I investigate whether causal probabilities indeed take the same values under their different possible definitions. (shrink)

This paper examines Patrick Suppes’ probabilistic theory of causality understood as a theory of causal inference, and draws some lessons for empirical economics and contemporary debates in the foundations of econometrics. It argues that a standard method of empirical economics, multiple regression, is inadequate for most but the simplest applications, that the Bayes’ nets approach, which can be understood as a generalisation of Suppes’ theory, constitutes a considerable improvement but is still subject to important limitations, and that the currently fashionable (...) ‘design-based approach’ suffers from the same flaws Suppes anticipated a long time ago. It then sketches an alternative in response, one that differs drastically from the formalisms Suppes endorsed but is consistent with his pragmatic general take on science. (shrink)

N. Cartwright's recent results on invariance under intervention and causality (2003) are reconsidered. Procedural approach to causality elicited in this paper and contrasted with Cartwright's apparently philosophical one unravels certain ramifications of her results. The procedural approach seems to license only a constrained notion of intervention and in consequence the "correctness to invariance" part of Cartwright's first theorem fails for a class of cases. The converse "invariance to correctness" part of the theorem relies heavily on modeling assumptions which prove to (...) be difficult to validate in practice and are often buttressed by independently acquired evidence. (shrink)

What Do the Data Tell Us? Justification of scientific theories is a three-place relation between data, theories, and background knowledge. Though this should be a commonplace, many methodologies in science neglect it. The article will elucidate the significance and function of our background knowledge in epistemic justification and their consequences for different scientific methodologies. It is argued that there is no simple and at the same time acceptable statistical algorithm that justifies a given theory merely on the basis of certain (...) data. And even if we think to know the probability of a theory, that does not decide whether we should accept it or not. (shrink)