Skip to main content
. Author manuscript; available in PMC: 2014 Dec 30.
Published in final edited form as: J Biopharm Stat. 2013;23(6):1383–1402. doi: 10.1080/10543406.2013.834912

Table 3.

Benefit in Power for Adjusted Analysis, N=1000, RD Treatment Effect = 9%

X Distribution βx Unadjusted Power Adjusted Power Benefit Unadjusted Bias
−0.6β̃tx 79.54% 79.22% −0.32% −0.1%
Normal −1.0β̃tx 78.76% 78.90% 0.14% −0.3%
   −1.5β̃tx 76.08% 78.46% 2.38% −0.5%

−0.6β̃tx 78.28% 78.92% 0.64% −0.3%
Lognormal −1.0β̃tx 76.66% 78.44% 1.78% −0.5%
−1.5β̃tx 71.96% 75.46% 3.50% −0.9%

−0.6β̃tx 79.52% 79.86% 0.34% −0.2%
Bimodal −1.0β̃tx 74.38% 77.38% 3.00% −0.7%
−1.5β̃tx 67.70% 73.80% 6.10% −1.4%