Inferring causal relations by modelling structures

I characterise and justify a type of causal reasoning which operates at the level of generalisation where laws are found. Much of the 'law-level causal influence’ (as I shall refer to it) which is the concern of science can be captured fairly straightforwardly within the structural equations framework but is crucially distinct from the level of causal influence characterised in the equations of causal models. This latter 'system- level causal influence’ has typically been the focus of philosophical engagement with structural equations significantly hampering discussion as a consequence. I aim to show how this limited focus has suppressed our understanding of the knowledge required to address known problems with procedures (both experimental and non-experimental) used to infer causal models. By bringing law-level causal influence to light and establishing the inferential relations which connect it with system-level causal influence I hope to show how reasoning at the law-level aids reasoning at the system-level. In the process it will also become clear how important the notion of a 'system’ is in our causal reasoning, as well as the conditions systems must satisfy in order to be described correctly by a causal model.

Causality in the Sciences, 2011

This paper deals with causal explanation in quantitative-oriented social sciences. In the framework of statistical modelling, we first develop a formal structural modelling approach which is meant to shape causal explanation. Recursive decomposition and exogeneity are given a major role for explaining social phenomena. Then, based on the main features of structural models, the recursive decomposition is interpreted as a mechanism and exogenous variables as causal factors. Arguments from statistical methodology are first offered and then submitted to critical evaluation.

Quality & Quantity

There is no unified theory of causality in the sciences and in philosophy. In this paper, we focus on a particular framework, called structural causal modelling (SCM), as one possible perspective in quantitative social science research. We explain how this methodology provides a fruitful basis for causal analysis in social research, for hypothesising, modelling, and testing explanatory mechanisms. This framework is not based on a system of equations, but on an analysis of multivariate distributions. In particular, the modelling stage is essentially distribution-free. Adopting an SCM approach means endorsing a particular view on modelling in general (the hypothetico-deductive methodology), and a specific stance on exogeneity (namely as a condition of separability of inference), on the one hand, and in interpreting marginal-conditional decompositions (namely as mechanisms), on the other hand.

The Springer Series on Demographic Methods and Population Analysis, 2009

This paper deals with causal analysis in the social sciences. We first present a conceptual framework according to which causal analysis is based on a rationale of variation and invariance, and not only on regularity. We then develop a formal framework for causal analysis by means of structural modelling. Within this framework we approach causality in terms of exogeneity in a structural conditional model based which is based on (i) congruence with background knowledge, (ii) invariance under a large variety of environmental changes, and (iii) model fit. We also tackle the issue of confounding and show how latent confounders can play havoc with exogeneity. This framework avoids making untestable metaphysical claims about causal relations and yet remains useful for cognitive and action-oriented goals.

IAP Statistics Network, Institut de Statistique, 2007

This paper deals with causal analysis in the social sciences. We first present a conceptual framework according to which causal analysis is based on a rationale of variation and invariance, and not only on regularity. We then develop a formal framework for causal analysis by means of structural modelling. Within this framework we approach causality in terms of exogeneity in a structural conditional model based on (i) model fit,(ii) invariance under a large variety of environmental changes, and (iii) congruence with ...

arXiv (Cornell University), 2022

Structural causal models (SCMs) are a widespread formalism to deal with causal systems. A recent direction of research has considered the problem of relating formally SCMs at different levels of abstraction, by defining maps between SCMs and imposing a requirement of interventional consistency. This paper offers a review of the solutions proposed so far, focusing on the formal properties of a map between SCMs, and highlighting the different layers (structural, distributional) at which these properties may be enforced. This allows us to distinguish families of abstractions that may or may not be permitted by choosing to guarantee certain properties instead of others. Such an understanding not only allows to distinguish among proposal for causal abstraction with more awareness, but it also allows to tailor the definition of abstraction with respect to the forms of abstraction relevant to specific applications.

Synthese, 2017

Disputatio

The advantage of examining causality from the perspective of modelling is thus that it puts us naturally closer to the practice of the sciences. This means being able to set up an interdisciplinary dialogue that contrasts and compares modelling practices in different fields, say economics and biology, medicine and statistics, climate change and physics. It also means that it helps philosophers looking for questions that go beyond the narrow ‘what-is-causality’ or ‘what-are-relata’ and thus puts causality right at the centre of a complex crossroad: epistemology/methodology, metaphysics, politics/ethics. This special issue collects nine papers that touch upon various scientific fields, from system biology to medicine to quantum mechanics to economics, and different questions, from explanation and prediction to the role of both true and false assumptions in modelling.

Journal of the American Statistical Association, 2005

Judea Pearl has been at the forefront of research in the burgeoning field of causal modeling, and Causality is the culmination of his work over the last dozen or so years. For philosophers of science with a serious interest in causal modeling, Causality is simply mandatory reading. Chapter 2, in particular, addresses many of the issues familiar from works such as Causation, Prediction and Search by Peter Spirtes, Clark Glymour, and Richard Scheines (New York: Springer-Verlag, 1993). But philosophers with a more general interest in causation will also profit from reading Pearl's book, especially the material in chapters 7, 9, and 10 (not to mention the delightful epilogue), which is selfcontained and less technical than other parts of the book. The present review is aimed primarily at readers of the second type. Pearl represents a system of causal relationships by a causal model. A causal model consists of a set of variables, a set of functions, and a probability measure representing our ignorance of the actual values of the variables. Each function generates an equation of the form V i = f i (V i1 ,…,V im), where V i is distinct from each V ij. These equations represent "mechanisms" whereby the value of one variable is causally determined by the values of others. Mechanisms differ from what philosophers call "laws" in that the former are asymmetric. If it is a law that Y = f(X) (and f is an invertible function), then it is also a law that X = f-1 (Y). By contrast, if a causal model contains the mechanism Y = f(X), then it will not also contain the mechanism X = f-1 (Y) (except in very special cases). The system of equations may be represented qualitatively in a directed graph, with an "arrow" drawn from V i to V j just in case V i figures in the function for V j. The directed graph representation greatly facilitates inferences about the model. A causal model may be used to evaluate counterfactuals of the following form: if the value of V i were v i , then the value of V j would be …. The resultant value of V j is determined by replacing the equation V i = f i (V i1 ,…,V im) with V i = v i , and then solving the resulting system of equations. This replacement indicates that V i is set directly to v i by an intervention from outside the system, rather than having its value causally determined by the values of the variables within the system. The intervention need not be miraculous: mechanisms are not inviolable laws, but rather ceteris paribus laws that can be disrupted by external interventions. Such an intervention will not affect the functional forms of the other mechanisms in the causal system: the mechanisms are autonomous. The bulk of Pearl's book deals with inference problems where we have only partial information about the causal system being modeled. Our partial information may be of various kinds. Observational evidence may give us information about probabilistic correlations between variables; background assumptions may give us information about the graphical structure; and con

Journal for General Philosophy of Science, 2014

One way the social scientists explain phenomena is by building structural models. These models are explanatory insofar as they manage to perform a recursive decomposition on an initial multivariate probability distribution, which can be interpreted as a mechanism. The social scientists should include the variables in the model on the basis of their function in the mechanism. This paper examines the notion of 'function' within structural modelling. We argue that 'functions' ought to be understood as the theoretical underpinnings of the causes, namely as the role that causes play in the functioning of the mechanism.

THEORIA. An International Journal for Theory, History and Foundations of Science, 2012

Editors' introduction to the special issue on the Causality and Explanation in the Sciences conference, held at the University of Ghent in September 2011.

Every Thing Must Go, 2007

1 3 5 7 9 10 8 6 4 2 in the case of metaphysics we find this situation: through the form of its works it pretends to be something that it is not Rudolf Carnap ant is a mass term for anteaters Daniel Dennett

The British Journal for the Philosophy of Science, 2013

What are scientific theories and how should they be represented? In this paper I propose a causal-structural account, according to which scientific theories are to be represented as sets of interrelated causal and credal nets. In contrast with other accounts of scientific theories (such as Sneedian structuralism, Kitcher's unificationist view, and Darden's theory of theoretical components), this leaves room for causality to play a substantial role. As a result, an interesting account of explanation is provided which sheds light on explanatory unification within a causalist framework. The theory of classical genetics is used as a case study. A Common Lacuna: Where is Causality? Woodward's Interventionist Account of Causation Causal Bayes Nets and Their Interrelations 6.1 Causal Bayes nets 6.2 Relations among causal nets 6.3 Credal nets and their interrelations The Theory of the Gene and its Causal Graph A First Exemplar: Stem Length in Pea Plants 8.1 Three crosses on stem length in pea plants 8.2 The causal graph for stem length in pea plants 8.3 Morgan's explanatory principles and the credal net for stem length in pea plants

Australasian Journal of Philosophy, 2024

[Note: forthcoming in AJP, publication year estimated] This paper introduces and defends a new principle for when a structural equation model is apt for analyzing actual causation. Any such analysis in terms of these models has two components: a recipe for reading claims of actual causation off an apt model, and an articulation of what makes a model apt. The primary focus in the literature has been on the first component. But the recently discovered problem of structural isomorphs has made the second especially pressing (Hall 2007; Hitchcock 2007a). Those with realist sympathies have reason to resist the standard response to this problem, which introduces a normative parameter into the metaphysics (Gallow 2021; Hall 2007; Halpern 2016b; Halpern and Hitchcock 2010, 2015; Menzies 2017). However, the only alternative solution in the literature leaves central questions unanswered (Blanchard and Schaffer 2017). I propose an independently motivated aptness requirement, Evident Mediation, that provides the missing details and resolves the structural isomorph problem without need for a normative parameter.