Abstract
A global measure of biomarker effectiveness is the Youden index, the maximum difference between sensitivity, the probability of correctly classifying diseased individuals, and 1-specificity, the probability of incorrectly classifying healthy individuals. The cut-point leading to the index is the optimal cut-point when equal weight is given to sensitivity and specificity. Using the delta method, we present approaches for estimating confidence intervals for the Youden index and corresponding optimal cut-point for normally distributed biomarkers and also those following gamma distributions. We also provide confidence intervals using various bootstrapping methods. A comparison of interval width and coverage probability is conducted through simulation over a variety of parametric situations. Confidence intervals via delta method are shown to have both closer to nominal coverage and shorter interval widths than confidence intervals from the bootstrapping methods.
Original language | English (US) |
---|---|
Pages (from-to) | 549-563 |
Number of pages | 15 |
Journal | Communications in Statistics Part B: Simulation and Computation |
Volume | 36 |
Issue number | 3 |
DOIs | |
State | Published - May 2007 |
Externally published | Yes |
Keywords
- Confidence intervals
- Optimal cut-point
- ROC curve
- Sensitivity and specificity
- Youden index
ASJC Scopus subject areas
- Modeling and Simulation
- Statistics and Probability