Figure - PMC

Skip to main content

View full-text article in PMC

. Author manuscript; available in PMC: 2024 Jul 10.

Published in final edited form as: Stat Methods Med Res. 2024 Mar 6;33(4):647–668. doi: 10.1177/09622802241233768

Figure 4. — The first panel in the figure displays the average of $|bias ({\hat{TCR}}_{1})|, |bias ({\hat{TCR}}_{2})|$ , and $|bias ({\hat{TCR}}_{3})|$ for each of the explored sample sizes. The second panel displays the average of $var ({\hat{TCR}}_{1}), var ({\hat{TCR}}_{2})$ , and $var ({\hat{TCR}}_{3})$ for each scenario. The third panel displays the average of $MSE ({\hat{TCR}}_{1}), MSE ({\hat{TCR}}_{2})$ , and $MSE ({\hat{TCR}}_{3})$ for each scenario. We see that for most scenarios, the Euclidean method had smaller bias than the Youden index. For all scenarios, the Euclidean method had smaller variance and MSE.