Visualization in Bayesian workflow

TL;DR

This paper emphasizes the importance of visualization throughout the Bayesian workflow, highlighting its role in model building, checking, and inference, especially for high-dimensional models used in applied research.

Contribution

It provides a comprehensive overview of visualization techniques tailored for each stage of Bayesian data analysis, extending beyond traditional trace plots.

Findings

Visualization aids in iterative model development and checking.

Effective visualization is crucial for high-dimensional Bayesian models.

Supports better inference and decision-making in Bayesian workflows.

Abstract

Bayesian data analysis is about more than just computing a posterior distribution, and Bayesian visualization is about more than trace plots of Markov chains. Practical Bayesian data analysis, like all data analysis, is an iterative process of model building, inference, model checking and evaluation, and model expansion. Visualization is helpful in each of these stages of the Bayesian workflow and it is indispensable when drawing inferences from the types of modern, high-dimensional models that are used by applied researchers.