Visualization in Bayesian Data Analysis.

Modern Bayesian statistical science commonly proceeds without reference to statistical graphics; both involve computation, but they are rarely considered to be connected. Traditional views about the usage of Bayesian statistics and statistical graphics result in a certain clash of attitudes between the two. Bayesians might do some exploratory data analysis (EDA) to start with, but once the model or class of models is specified, the next analytical step is to fit the data; graphs are then typically used to check convergence of simulations, or they are used as teaching aids or as presentation tools - but not as part of the data analysis. Exploratory data analysis appears to have no formal place in Bayesian statistics once amodel has actually been fitted.According to this extreme view, the only connection between Bayesian inference and graphics occurs through convergence plots ofMarkov chain simulations, and histograms and kernel density plots of the resulting estimates of scalar parameters. [ABSTRACT FROM AUTHOR]