The experiment is just as important as the likelihood in understanding the prior: a cautionary note on robust cognitive modeling

Lauren Kennedy, Daniel Simpson, Andrew Gelman

Research output: Contribution to journalArticleResearchpeer-review


Cognitive modeling shares many features with statistical modeling, making it seem trivial to borrow from the practices of robust Bayesian statistics to protect the practice of robust cognitive modeling. We take one aspect of statistical workflow—prior predictive checks—and explore how they might be applied to a cognitive modeling task. We find that it is not only the likelihood that is needed to interpret the priors, we also need to incorporate experiment information as well. This suggests that while cognitive modeling might borrow from statistical practices, especially workflow, care must be taken to make the necessary adaptions.
Original languageEnglish
Pages (from-to)210-217
Number of pages8
JournalComputational Brain & Behavior
Publication statusPublished - 2019
Externally publishedYes


  • Bayesian statistics
  • Robust modeling
  • Cognitive modeling

Cite this