Comparison of the Frequentist MATA Confidence Interval with Bayesian Model-Averaged Confidence Intervals

Figure 1

Expected mean rainfall for seeded, stationary clouds, under each model and using model averaging. Vertical bars show 95% intervals for each prediction. Intervals shown: Bayesian and MAB (purple), Wald and MATA-Wald (orange), and profile likelihood and MATA-PL (blue).