12 papers
To select or not to select: predictively consistent priors instead of model selection
Anna Elisabeth Riha, Leevi Lindgren, David Kohns +2
Bayesian modelling workflows often consider multiple candidate models of varying complexity. Model selection is commonly used to navigate potential trade-offs between model complex…
LOO-PIT predictive model checking
Herman Tesso, Aki Vehtari
We consider predictive checking for Bayesian model assessment using leave-one-out probability integral transform (LOO-PIT). LOO-PIT values are conditional cumulative predictive pro…
Bridge Sampling Diagnostics
Giorgio Micaletto, Aki Vehtari
In Bayesian statistics, the marginal likelihood is used for model selection and averaging, yet it is often challenging to compute accurately for complex models. Approaches such as…
Amortized Bayesian Workflow
Chengkun Li, Aki Vehtari, Paul-Christian Bürkner +3
Bayesian inference often faces a trade-off between computational speed and sampling accuracy. We propose an adaptive workflow that integrates rapid amortized inference with gold-st…
Predictive Assessment and Comparison of Bayesian Survival Models for Cancer Recurrence
Saku Suorsa, Aki Vehtari
Complex data features, such as unmodelled censored event times and variables with time-dependent effects, are common in cancer recurrence studies and pose challenges for Bayesian s…
Uncertainty in Bayesian Leave-One-Out Cross-Validation Based Model Comparison
Tuomas Sivula, MÃ¥ns Magnusson, Asael Alonzo Matamoros +1
It is useful to estimate the expected predictive performance of models planned to be used for prediction. We focus on leave-one-out cross-validation (LOO-CV), which has become a po…