Rejoinder: More Limitations of Bayesian Leave-One-Out Cross-Validation

Open Access
Authors
Publication date 03-2019
Journal Computational Brain & Behavior
Volume | Issue number 2 | 1
Pages (from-to) 35-47
Organisations
  • Faculty of Social and Behavioural Sciences (FMG) - Psychology Research Institute (PsyRes)
Abstract We recently discussed several limitations of Bayesian leave-one-out cross-validation (LOO) for model selection. Our contribution attracted three thought-provoking commentaries. In this rejoinder, we address each of the commentaries and identify several additional limitations of LOO-based methods such as Bayesian stacking. We focus on differences between LOO-based methods versus approaches that consistently use Bayes’ rule for both parameter estimation and model comparison. We conclude that LOO-based methods do not align satisfactorily with the epistemic goal of mathematical psychology.
Document type Article
Note In special issue: Leave-one-out Cross-Validation, and Issues in Practical Model Selection.
Language English
Published at https://doi.org/10.1007/s42113-018-0022-4
Downloads
Permalink to this page
Back