Skip to main content
. Author manuscript; available in PMC: 2016 Mar 1.
Published in final edited form as: J Am Stat Assoc. 2014 Oct 2;110(509):27–44. doi: 10.1080/01621459.2014.964404

Table 2.

Frequentist coverage of 50% (top row) and 95% (bottom row) Bayesian credible intervals, for various parameters. Data sets were generated with three true correlation levels: 0.5, 0.8, 0.9.

Coverage for parameters
True φ1,2 Confidence φ1,2 ξk θj Gk νj
ηk1
ηk0
φ1,2 = 0.5 50% 43% 51% 39% 49% 40% 56% 54%
95% 92% 95% 82% 94% 86% 96% 96%

φ1,2 = 0.8 50% 43% 50% 39% 45% 41% 55% 54%
95% 94% 95% 82% 92% 83% 96% 96%

φ1,2 = 0.9 50% 49% 50% 40% 46% 39% 54% 54%
95% 98% 95% 82% 93% 84% 96% 97%