A Ramsey Test Analysis of Causation for Causal Models

Andreas, Holger; Günther, Mario

doi:10.1093/bjps/axy074

Cited by 10 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The importance of this issue is highlighted by counterfactual approaches to causation coming from philosophy (Collins et al, 2004; Goodman, 1947; Lewis, 1973a), computer science (Pearl, 2009), and statistics (Morgan & Winship, 2018; VanderWeele, 2015). Recently, various authors in psychology and philosophy have also made a case for causal interpretations of indicative conditionals (e.g., Andreas & Günther, 2018; Oaksford & Chater, 2017; van Rooij & Schulz, 2019; Vandenburgh, 2020).…”

Section: Indicative Conditionals and Probabilitiesmentioning

confidence: 99%

See 1 more Smart Citation

Conditionals and the hierarchy of causal queries.

Skovgaard-Olsen¹,

Stephan²,

Waldmann³

2021

Journal of Experimental Psychology: General

View full text Add to dashboard Cite

Recent studies indicate that indicative conditionals like "If people wear masks, the spread of Covid-19 will be diminished" require a probabilistic dependency between their antecedents and consequents to be acceptable (Skovgaard-Olsen et al., 2016). But it is easy to make the slip from this claim to the thesis that indicative conditionals are acceptable only if this probabilistic dependency results from a causal relation between antecedent and consequent.According to Pearl ( 2009), understanding a causal relation involves multiple, hierarchically organized conceptual dimensions: prediction, intervention, and counterfactual dependence. In a series of experiments, we test the hypothesis that these conceptual dimensions are differentially encoded in indicative and counterfactual conditionals. If this hypothesis holds, then there are limits as to how much of a causal relation is captured by indicative conditionals alone. Our results show that the acceptance of indicative and counterfactual conditionals can become dissociated. Furthermore, it is found that the acceptance of both is needed for accepting a causal relation between two co-occurring events. The implications that these findings have for the hypothesis above, and for recent debates at the intersection of the psychology of reasoning and causal judgment, are critically discussed. Our findings are consistent with viewing indicative conditionals as answering predictive queries requiring evidential relevance (even in the absence of direct causal relations). Counterfactual conditionals in contrast target causal relevance, specifically. Finally, we discuss the implications our results have for the yet unsolved question of how reasoners succeed in constructing causal models from verbal descriptions.

show abstract

Section: Indicative Conditionals and Probabilitiesmentioning

confidence: 99%

“…Recently, various authors in psychology and philosophy have also made a case for causal interpretations of indicative conditionals (e.g. Oaksford & Chater, 2017;Andreas & Günther, 2018;van Rooij & Schulz, 2019;Vandenburgh, 2020).…”

Section: Introductionmentioning

confidence: 99%

Conditionals and the hierarchy of causal queries.

Skovgaard-Olsen¹,

Stephan²,

Waldmann³

2021

Journal of Experimental Psychology: General

View full text Add to dashboard Cite

show abstract

“…With a bit of weakening, the (set of) closestpossible-world(s) can be interpreted as the (set of) close-enough-possibleworld(s), where due to practical considerations those possible worlds that are close enough to the actual world (rather than the closest possible worlds) are selected. For a recent alternative to evaluating conditionals relative to a causal model see [1].…”

Section: Introductionmentioning

confidence: 99%

“…These approaches are most often rooted, implicitly or explicitly, in either of the two prominent conceptual approaches for evaluating counterfactuals: the closeenough-possible-worlds approach inspired by Lewis [36] and Stalnaker [49], and the causal modeling approach developed by Spirtes et al [48] and Pearl [44], among others. 1 To evaluate a counterfactual, the close-enough-possibleworlds approach compares the actual world in which X and Y occur with those similar-enough worlds to the actual world in which X does not occur (e.g., comparing a data instance 1 Strictly speaking, [36,49] develop the closest-possible-worlds approach to make sense of counterfactuals. With a bit of weakening, the (set of) closestpossible-world(s) can be interpreted as the (set of) close-enough-possibleworld(s), where due to practical considerations those possible worlds that are close enough to the actual world (rather than the closest possible worlds) are selected.…”

Section: Introductionmentioning

confidence: 99%

“…However, the novelty of our contribution is threefold. (1) We provide a conceptual analysis of the vagueness of the notion of 'similarity', rooted in the closeenough-possible-worlds approach. This approach is the conceptual basis of feature-based, prototype, and example-based analytic methods for examining counterfactuals by machine learning community.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The Use and Misuse of Counterfactuals in Ethical Machine Learning

Kasirzadeh

Smart

2021

Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency

View full text Add to dashboard Cite

The use of counterfactuals for considerations of algorithmic fairness and explainability is gaining prominence within the machine learning community and industry. This paper argues for more caution with the use of counterfactuals when the facts to be considered are social categories such as race or gender. We review a broad body of papers from philosophy and social sciences on social ontology and the semantics of counterfactuals, and we conclude that the counterfactual approach in machine learning fairness and social explainability can require an incoherent theory of what social categories are. Our findings suggest that most often the social categories may not admit counterfactual manipulation, and hence may not appropriately satisfy the demands for evaluating the truth or falsity of counterfactuals. This is important because the widespread use of counterfactuals in machine learning can lead to misleading results when applied in high-stakes domains. Accordingly, we argue that even though counterfactuals play an essential part in some causal inferences, their use for questions of algorithmic fairness and social explanations can create more problems than they resolve. Our positive result is a set of tenets about using counterfactuals for fairness and explanations in machine learning. CCS CONCEPTS • Computing methodologies → Philosophical/theoretical foundations of artificial intelligence; Machine learning; • Social and professional topics → Socio-technical systems; Race and ethnicity.

show abstract