Skip to main content

Table 4 Empirical power according to the different input parameters in setting 1 (exponential case) using both measures (gAHR/nHR)

From: Using the geometric average hazard ratio in sample size calculation for time-to-event data with composite endpoints

   Power descriptive
  s Min Q1 Med Q3 Max
Treatment effect       
Any HRj=0.6 225/225 0.784/0.215 0.795/0.601 0.798/0.765 0.801/0.882 0.809/0.995
HR1=HR2=0.9 36/42 0.789/0.727 0.798/0.762 0.801/0.775 0.803/0.786 0.808/0.799
Other cases 135/135 0.790/0.466 0.797/0.696 0.800/0.771 0.802/0.836 0.811/0.952
Observed proportions       
Any \(p_{j}^{(0)}=0.05\) 180/186 0.784/0.215 0.795/0.650 0.798/0.777 0.801/0.867 0.809/0.995
\(p_{1}^{(0)}=p_{2}^{(0)} \ge 0.3\) 81/81 0.790/0.536 0.797/0.708 0.800/0.764 0.803/0.791 0.810/0.901
Other cases 135/135 0.788/0.274 0.796/0.612 0.799/0.764 0.802/0.877 0.811/0.986
Correlation       
Weak (ρ=0.1) 132/134 0.788/0.251 0.796/0.698 0.798/0.789 0.802/0.855 0.811/0.995
Mild (ρ=0.3) 132/134 0.785/0.239 0.796/0.671 0.799/0.767 0.802/0.844 0.809/0.994
Moderate (ρ=0.5) 132/134 0.784/0.215 0.796/0.654 0.799/0.751 0.802/0.831 0.810/0.993
Global 396/402 0.784/0.215 0.796/0.678 0.799/0.771 0.802/0.845 0.811/0.995
  1. First column (s) is the number of scenarios. Min: minimum; Q1: first quartile; Med: Median; Q3: third quartile; Max: maximum