Receiver operating characteristic (ROC) curves are an established method for
assessing the predictive capacity of a continuous biomarker for a binary
outcome. However, in some cases, outcomes are time dependent. Although the
literature has proposed packages for performing ROC analysis of time-independent
outcomes, a package is not yet available for analyzing the predictive capacity
of continuous biomarkers when the binary outcome is time dependent. In this
article, we present stroccurve, a new command for
performing ROC analysis within a survival framework.
AkritasM. G.1994. Nearest neighbor estimation of a bivariate
distribution under random censoring. Annals of
Statistics22: 1299–1327.
2.
FlemingT. R., and
HarringtonD. P.1991. Counting Processes and Survival Analysis.New York:
Wiley.
3.
HeagertyP. J., LumleyT., and PepeM. S.2000. Time-dependent ROC curves for censored
survival data and a diagnostic marker.
Biometrics56: 337–344.
4.
KaplanE. L., and MeierP.1958. Nonparametric estimation from incomplete
observations. Journal of the American Statistical
Association53: 457–481.
5.
LiuX., and JinZ.2015. Optimal survival time-related cut-point with
censored data. Statistics in Medicine34: 515–524.
6.
PepeM. S., LongtonG., and JanesH.2009. Estimation and comparison of receiver
operating characteristic curves. Stata
Journal9: 1–16.
7.
PerkinsN. J., and
SchistermanE. F.2006. The inconsistency of “optimal” cutpoints
obtained using two criteria based on the receiver operating characteristic
curve. American Journal of Epidemiology163: 670–675.
8.
YoudenW. J.1950. Index for rating diagnostic
tests. Cancer3: 32–35.
