Bayesian Nonparametric Modeling of Individual Differences: A Case Study Using Decision-Making on Bandit Problems

Abstract

We develop and compare two non-parametric Bayesian approaches for modeling individual differences in cognitive processes. These approaches both allow major discrete differences between groups of people to be modeled, without making strong prior assumptions about how many groups are required. Instead, the number of groups can naturally grow as more information about the behavior of people becomes available. One of our models extends previous work by allowing continuous differences between people within the same group to be modeled. We demonstrate both approaches in a case study using a classic heuristic model of human decision-making on bandit problems, applied to previously reported behavioral data from 451 participants. We conclude that the ability to model both discrete and continuous aspects of individual differences in cognition is important, and that non-parametric approaches are well suited for inferring these types of differences from empirical data.


Back to Friday Papers