Skip to main content
. Author manuscript; available in PMC: 2014 Jan 21.
Published in final edited form as: Biometrics. 2012 May 2;68(4):1103–1112. doi: 10.1111/j.1541-0420.2012.01762.x

Table 3.

Percent efficiency gain over non-robust Bayesian models, stratified by minimum run length.

minimum run length
0 1 2 3 4 5
default priors
original, norm mix 7 10 11 10 9 6
original, LAR(1) 9 12 14 15 16 15
g-h, LAR(1) 10 12 15 15 15 12
substantive priors
original, norm mix 8 11 13 13 12 9
original, LAR(1) 10 14 17 19 20 19
g-h, LAR(1) 16 20 23 27 28 28