Probabilistic Causation

2017 ◽  
Author(s):  
Christopher Hitchcock
Keyword(s):  
Conditional Probability ◽  
Causal Relations ◽  
Probabilistic Causation ◽  
Bayes Nets ◽  
Actual Causation ◽  
Singular Causation ◽  
Causal Bayes Nets ◽  
Causal Strength

This chapter will explore a variety of projects that aim to characterize causal concepts using probability. These are, somewhat arbitrarily, divided into four categories. First, a tradition within philosophy that has aimed to define, or at least constrain, causation in terms of conditional probability is discussed. Secondly, the use of causal Bayes nets to represent causal relations, to facilitate inferences from probabilities to causal relations, and to ‘identify’ causal quantities in probabilistic terms is discussed. Thirdly, efforts to measure causal strength in probabilistic terms are reviewed, with particular attention to the significance of these measures in the context of epidemiology. Finally, attempts are discussed to analyze the relation of ‘actual causation’ (sometimes called ‘singular causation’) using probability.

Causal Models and Conditional Reasoning

2017 ◽  
Author(s):  
Mike Oaksford ◽  
Nick Chater
Keyword(s):  
Model Theory ◽  
Causal Model ◽  
Recent Model ◽  
Causal Models ◽  
Conditional Reasoning ◽  
Cognitive System ◽  
Markov Condition ◽  
Bayes Nets ◽  
Causal Bayes Nets ◽  
Conditional Statements

There are deep intuitions that the meaning of conditional statements relate to probabilistic law-like dependencies. In this chapter it is argued that these intuitions can be captured by representing conditionals in causal Bayes nets (CBNs) and that this conjecture is theoretically productive. This proposal is borne out in a variety of results. First, causal considerations can provide a unified account of abstract and causal conditional reasoning. Second, a recent model (Fernbach & Erb, 2013) can be extended to the explicit causal conditional reasoning paradigm (Byrne, 1989), making some novel predictions on the way. Third, when embedded in the broader cognitive system involved in reasoning, causal model theory can provide a novel explanation for apparent violations of the Markov condition in causal conditional reasoning (Ali et al, 2011). Alternative explanations are also considered (see, Rehder, 2014a) with respect to this evidence. While further work is required, the chapter concludes that the conjecture that conditional reasoning is underpinned by representations and processes similar to CBNs is indeed a productive line of research.

scholarly journals Norms and high-level cognition: Consequences, trends, and antidotes

2011 ◽  
Vol 34 (5) ◽  
pp. 260-261
Author(s):  
Simon McNair ◽  
Aidan Feeney
Keyword(s):  
Bayes Nets ◽  
Psychological Science ◽  
Causal Bayes Nets ◽  
High Level

AbstractWe are neither as pessimistic nor as optimistic as Elqayam & Evans (E&E). The consequences of normativism have not been uniformly disastrous, even among the examples they consider. However, normativism won't be going away any time soon and in the literature on causal Bayes nets new debates about normativism are emerging. Finally, we suggest that to concentrate on expert reasoners as an antidote to normativism may limit the contribution of research on thinking to basic psychological science.

Towards a New Model for Causal Reasoning in Expert Systems

2017 ◽  
Vol 7 (1) ◽  
pp. 32-63 ◽  
Author(s):  
M. Keith Wright
Keyword(s):  
Expert Systems ◽  
Conditional Probability ◽  
Causal Reasoning ◽  
Causal Theory ◽  
Probability Judgment ◽  
Probability Assessment ◽  
Conditional Probabilities ◽  
Long Run ◽  
Causal Strength ◽  
As If

This paper presents ideas for improved conditional probability assessment and improved expert systems consultations. It cautions that knowledge engineers may sometimes be imprecise when capturing causal information from experts: their elicitation questions may not distinguish between causal and correlational expertise. This paper shows why and how such models cannot support normative inferencing over conditional probabilities as if they were all based on frequencies in the long run. In some cases, these probabilities are instead causal theory-based judgments, and therefore are not traditional conditional probabilities. This paper argues that these should be processed as if they were causal strength probabilities or causal propensity probabilities. This paper reviews the literature on causal and probability judgment, and then presents a probabilistic inferencing model that integrates theory-based causal probabilities with frequency-based conditional probabilities. The paper also proposes guidelines for elicitation questions that knowledge engineers may use to avoid conflating causal theory-based judgment with frequency based judgment.

scholarly journals The interplay between covariation, temporal, and mechanism information in singular causation judgments

2021 ◽  
Author(s):  
Simon Stephan ◽  
Michael R. Waldmann
Keyword(s):  
Computational Model ◽  
Causal Attribution ◽  
Future Research ◽  
Spatiotemporal Location ◽  
The Past ◽  
Singular Causation ◽  
Causal Judgments ◽  
Causal Strength ◽  
Causal Cognition ◽  
Psychological Studies

Most psychological studies on causal cognition have focused on how people make predictions from causes to effects or how they assess causal strength for general causal relationships (e.g., “smoking causes cancer”). In the past years, there has been a surge of interest in other types of causal judgments, such as diagnostic inferences or causal selection. Our focus here is on how people assess singular causation relations between cause and effect events that occurred at a particular spatiotemporal location (e.g., “Mary’s having taking this pill caused her sickness.”). The analysis of singular causation has received much attention in philosophy, but relatively few psychological studies have investigated how lay people assess these relations. Based on the power PC model of causal attribution proposed by Cheng and Novick (2005), we have developed and tested a new computational model of singular causation judgments integrating covariation, temporal, and mechanism information. We provide an overview of this research and outline important questions for future research.

scholarly journals Probabilistic language in indicative and counterfactual conditionals

2017 ◽  
Vol 27 ◽  
pp. 525
Author(s):  
Daniel Lassiter
Keyword(s):  
Structural Equation ◽  
Structural Equation Models ◽  
Compositional Semantics ◽  
Direct Role ◽  
Revision Procedure ◽  
Counterfactual Conditionals ◽  
Bayes Nets ◽  
Causal Bayes Nets ◽  
Probability Operators

This paper analyzes indicative and counterfactual conditionals that have in their consequents probability operators: probable, likely, more likely than not, 50% chance and so on. I provide and motivate a unified compositional semantics for both kinds of probabilistic conditionals using a Kratzerian syntax for conditionals and a representation of information based on Causal Bayes Nets. On this account, the only difference between probabilistic indicatives and counterfactuals lies in the distinction between conditioning and intervening. This proposal explains why causal (ir)relevance is crucial for probabilistic counterfactuals, and why it plays no direct role in probabilistic indicatives. I conclude with some complexities related to the treatment of backtracking counterfactuals and subtleties revealed by probabilistic language in the revision procedure used to create counterfactual scenarios. In particular, I argue that certain facts about the interaction between probability operators and counterfactuals motivate the use of Structural Equation Models (Pearl 2000) rather than the more general formalism of Causal Bayes Nets.

Singular Causation

2017 ◽  
Author(s):  
David Danks
Keyword(s):  
Physical Process ◽  
Causal Relations ◽  
Cause And Effect ◽  
Singular Causation ◽  
Psychological Theories ◽  
Difference Making ◽  
The World ◽  
Similarities And Differences

Causal relations between specific events are often critically important for learning, understanding, and reasoning about the world. This chapter examines both philosophical accounts of the nature of singular causation, and psychological theories of people’s judgments and reasoning about singular causation. It explores the content of different classes of theories, many of which are based on either some type of physical process connecting cause and effect, or else some kind of difference-making (or counterfactual) impact of the cause on the effect. In addition, this chapter examines various theoretical similarities and differences, particularly between philosophical and psychological theories that appear superficially similar. One consistent theme that emerges in almost every account is the role of general causal relations in shaping human judgments and understandings about singular causation.

Sign in / Sign up

Export Citation Format

Share Document