Comparison of bandwidth selection methods for kernel smoothing of ROC curves

Statistics in Medicine

Volumn 21, Issue 14, 2002, Pages 2045-2055

  Zhou, Xiao Hua ^a   Harezlak, Jaroslaw ^a  

^a INDIANA UNIVERSITY   (United States)

Author keywords

Bandwidth selection; Continuous scale test; Empirical ROC curve; Kernel smoothing

Indexed keywords

ANALYTIC METHOD; ARTICLE; CONTROLLED STUDY; INTERMETHOD COMPARISON; NONPARAMETRIC TEST; PROCESS MODEL; RECEIVER OPERATING CHARACTERISTIC; SAMPLE SIZE; STATISTICAL DISTRIBUTION;

COMPUTER SIMULATION; HUMANS; PANCREATIC NEOPLASMS; ROC CURVE; STATISTICS, NONPARAMETRIC;

EID: 0037199385     PISSN: 02776715     EISSN: None     Source Type: Journal    
DOI: 10.1002/sim.1156     Document Type: Article

References (13)

1. Receiver operating characteristic (ROC) plots: A fundamental evaluation tool in clinical medicine
2. Two transformation models for estimating an ROC curve derived from continuous data
3. The interpretation of diagnostic tests
4. Receiver operating characteristic (ROC) analysis
5. Nonparametric and semiparametric estimation of the receiver operating characteristics curve
6. Smooth non-parametric receiver operating characteristic curves for continuous diagnostic tests
7. Using smooth receiver operating characteristic curves to summarize and compare diagnostic systems
8. Kernel estimators of the ROC curve are better than empirical
9. Bandwidth selection for the smoothing of distribution functions
10. Bandwidth selection for kernel distribution function estimation
11. Some aspects of ROC curve-fitting: Normal and logistic models