Projects

Supporting Bayesian workflows with iterative filtering for multiverse analysis

When building statistical models for Bayesian data analysis tasks, required and optional iterative adjustments and different modelling choices can give rise to numerous candidate models. Checks and evaluations throughout the modelling process can motivate changes to an existing model or the consideration of alternatives. Failing to consider alternative models can lead to overconfidence in the predictive or inferential ability of a chosen model. The search for suitable models requires modellers to work with multiple models without jeopardising the validity of their results. Multiverse analysis enables the transparent creation of several models based on different modelling choices, but the number of models can become overwhelming in practice, and we require tools to reduce sets of models towards fewer models of higher quality across different modelling contexts. Motivated by these challenges, this work proposes iterative filtering for multiverse analysis to support efficient and consistent assessment of multiple models. Given that causal constraints have been considered, we show how multiverse analysis can be combined with recommendations from established Bayesian modelling workflows to identify promising candidate models by assessing predictive abilities and, if needed, tending to computational issues. We illustrate our suggested approach in different realistic modelling scenarios using real data examples.