Skip to main content
Fig. 1 | BMC Medical Research Methodology

Fig. 1

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

Fig. 1

ZODIAC trial. HR∗(t) over time in 5 plausible scenarios for the ZODIAC trial: 1) weak correlation (ρ=0.1) and constant hazards for OS and TTP; The remaining scenarios have moderate correlation (ρ=0.5) but with different hazard behavior for OS and TTP: 2) both constant (OS and TTP); 3) constant (OS) and increasing (TTP); 4) constant (OS) and decreasing (TTP); and 5) increasing (OS) and decreasing (TTP)

Back to article page

BMC Medical Research Methodology

ISSN: 1471-2288

Contact us