Troubleshooting Bayesian cognitive models.

Abstract

Using Bayesian methods to apply computational models of cognitive processes, or Bayesian cognitive modeling, is an important new trend in psychological research. The rise of Bayesian cognitive modeling has been accelerated by the introduction of software that efficiently automates the Markov chain Monte Carlo sampling used for Bayesian model fitting—including the popular Stan and PyMC packages, which automate the dynamic Hamiltonian Monte Carlo and No-U-Turn Sampler (HMC/NUTS) algorithms that we spotlight here. Unfortunately, Bayesian cognitive models can struggle to pass the growing number of diagnostic checks required of Bayesian models. If any failures are left undetected, inferences about cognition based on the model’s output may be biased or incorrect. As such, Bayesian cognitive models almost always require troubleshooting before being used for inference. Here, we present a deep treatment of the diagnostic checks and procedures that are critical for effective troubleshooting, but are often left underspecified by tutorial papers. After a conceptual introduction to Bayesian cognitive modeling and HMC/NUTS sampling, we outline the diagnostic metrics, procedures, and plots necessary to detect problems in model output with an emphasis on how these requirements have recently been changed and extended. Throughout, we explain how uncovering the exact nature of the problem is often the key to identifying solutions. We also demonstrate the troubleshooting process for an example hierarchical Bayesian model of reinforcement learning, including supplementary code. With this comprehensive guide to techniques for detecting, identifying, and overcoming problems in fitting Bayesian cognitive models, psychologists across subfields can more confidently build and use Bayesian cognitive models in their research.

Forget and Forgive: A Neurocognitive Mechanism for Increased Cooperation During Group Formation

“…For each of the models, we generated 4 independent chains of 2000 samples (with 1000 burn-in) from the joint posterior distribution. Following recent recommendations 75 , we use as a diagnostic of proper chain mixing, reflecting a reliable parameter estimate. statistic reflects the proportion of between-to-within chain variance.…”

“…Following recent recommendations 75 , we use as a diagnostic of proper chain mixing, reflecting a reliable parameter estimate. statistic reflects the proportion of between-to-within chain variance.…”

High stakes slow responding, but do not help overcome Pavlovian biases in humans

“…For each model, we used four chains with 10,000 iterations each (5,000 as warm-up), yielding a total of 20,000 samples contributing to the posteriors. We checked that Rhats for all parameters were below 1.01, effective sample sizes for all parameters were at least 400, that chains were stationary and well-mixing (using trace plots), that the Bayesian fraction of missing information (BFMI) for each chain was above 0.2, and that (if possible) no divergent transitions occurred (Baribault & Collins, 2023). To minimize the occurrence of divergent transitions, we increased the target average proposal acceptance probability (adapt_delta) to 0.99.…”

Motivational context determines the impact of aversive outcomes on mental effort allocation

“…We ran 5 parallel chains for 12000 iterations each, discarded the first 8000 warm-up samples, and kept the remaining 4000 samples as posterior estimates (20000 samples total). The Gelman-Rubin convergence diagnostic Rhat (Gelman & Rubin, 1992) was used to assess model convergence (Rhats close to 1 indicates convergence; we considered a model successfully converged with Rhats <= 1.01 (Baribault & Collins, 2023).…”