Evaluating the inverse reasoning account of object discovery

Abstract

People routinely make inferences about unobserved objects. A hotel guest with welts on his arms, for example, will often worry about bed bugs. The discovery of unobserved objects almost always involves a backward inference from some observed effects (e.g., welts) to unobserved causes (e.g., bed bugs). The inverse reasoning account, which is typically formalized as Bayesian inference, posits that the strength of a backward inference is closely connected to the strength of the corresponding forward inference from the unobserved causes to the observed effects. We evaluated the inverse reasoning account of object discovery in three experiments where participants were asked to discover the unobserved “attractors” and “repellers” that controlled a “particle” moving within an arena. Experiments 1 and 2 showed that participants often failed to provide the best explanations for various particle motions, even when the best explanations were simple and when participants enthusiastically endorsed these explanations when presented with them. This failure demonstrates that object discovery is critically dependent on the processes that support hypothesis generation—processes that the inverse reasoning account does not explain. Experiment 3 demonstrated that people sometimes generate explanations that are invalid even according to their own forward inferences, suggesting that the psychological processes that support forward and backward inference are less intertwined than the inverse reasoning account suggests. The experimental findings support an alternative account of object discovery in which people rely on heuristics to generate possible explanations.