Categorical induction from uncertain premises: Jeffrey's doesn't completely rule

Widening Access to Bayesian Problem Solving

Bayesian reasoning and decision making is widely considered normative because it minimizes prediction error in a coherent way. However, it is often difficult to apply Bayesian principles to complex real world problems, which typically have many unknowns and interconnected variables. Bayesian network modeling techniques make it possible to model such problems and obtain precise predictions about the causal impact that changing the value of one variable may have on the values of other variables connected to it. But Bayesian modeling is itself complex, and has until now remained largely inaccessible to lay people. In a large scale lab experiment, we provide proof of principle that a Bayesian network modeling tool, adapted to provide basic training and guidance on the modeling process to beginners without requiring knowledge of the mathematical machinery working behind the scenes, significantly helps lay people find normative Bayesian solutions to complex problems, compared to generic training on probabilistic reasoning. We discuss the implications of this finding for the use of Bayesian network software tools in applied contexts such as security, medical, forensic, economic or environmental decision making.

Why the Conjunction Effect Is Rarely a Fallacy: How Learning Influences Uncertainty and the Conjunction Rule

In this article we explore the relationship between learning and the conjunction fallacy. The interpretation of the conjunction effect as a fallacy assumes that all observers share the same knowledge, and that nobody has access to privileged information. Such situations are actually quite rare in everyday life. Building on an existing model of surprise, we prove formally that in the more typical scenarios, where observers are alert to the possibility of learning from event outcomes, the conjunction rule does not apply. Scenarios which have been engineered to produce the so-called conjunction “fallacy” (e.g., Tverksy and Kahneman, 1983) often imply subjective uncertainty and hence the possibility of learning. In Experiment 1 we demonstrate that when these scenarios are rephrased so as to eliminate subjective uncertainty, the effect is mitigated. In Experiment 2 we demonstrate that when subjective uncertainty is reduced by allowing participants to learn about the mechanism behind a conjunction-inducing scenario, the conjunction effect again diminishes. We conclude that the conjunction effect arises due to the unnaturalness of interpreting verbal descriptions in terms of a situation in which all observers share the same knowledge. Instead, when people hear descriptions of real world situations, they are likely to assume that learning is possible, and that subjective rather than objective uncertainty applies.