IS BAYESIAN UPDATING MODALITY-DEPENDENT?

In a Bayesian perspective, the probabilistic dependencies between hypotheses under consideration and diagnostic pieces of evidence are the only relevant information for probabilistic updating. We investigated whether human probability judgments conform to this assumption, by manipulating the sensory systems involved in the acquisition and processing of information concerning evidence and hypotheses. Hence, we ran five (computer-based) experiments using a variant of the classic book bag and poker chip task (e.g., Phillips & Edwards, 1966). Participants were first presented with pairs of urns A and B filled with a different proportion of balls that turned either red or green in the visual condition, balls that emitted either a low- or high-pitched sound in the auditory condition, and balls that both turned a color and emitted a sound in various cross-modal (i.e., audio-visual) conditions. One urn was then selected at random, some balls were randomly drawn from it, and their color and/or sound were disclosed. Participants’ task was to estimate the probability that each of the two urns has been selected, given the information provided. In Experiments 1 and 2, we compared the probability judgments referring to probabilistically identical visual and auditory scenarios that only differed with regards to the sensory system involved, without finding any difference between the answers provided in the two conditions. In Experiment 3, 4, and 5, the addition of cross-modal scenarios allowed us to investigate the effects on probabilistic updating of synergic (i.e., both visual and auditory evidence individually supported the hypothesis they jointly supported) or contrasting (i.e., either visual and/or auditory evidence individually supported the hypothesis opposite the one they jointly supported) audio-visual evidence. Our results provide evidence in favor of a synergy-contrasting effect, as probability judgments were more accurate in synergic conditions than in contrasting conditions. This suggests that, when perceptual information is acquired through a singular sensory system, probability judgments conform to the Bayesian assumption that the sensory system involved does not play a role in the updating process, whereas the simultaneous presentation of cross-modal information can influence participants’ performance.