Improved methods for bandwidth selection when estimating ROC curves.

DOI10.1016/S0167-7152(03)00150-0MaRDI QIDQ1423137zbMATH OpenOpenAlexWikidataFDO

Authors Rob J. Hyndman, Peter Hall

Publication date 14 February 2004

Published in Statistics \& Probability Letters (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/s0167-7152(03)00150-0

zbMATH Keywords

ROCcurveMISEBandwidth selectionKernel estimatorBinary classification

Mathematics Subject Classification ID

Density estimation (62G07)

Recommendations

• A Flexible Method for Estimating the ROC Curve
• Confidence intervals and bands for the binormal ROC curve revisited
• ROC curves determination by nonparametric methods
• Estimation of a convex ROC curve.
• Comparing the estimates of ROC curves by modeling methods
• scientific article; zbMATH DE number 6445233
• A semiparametric method for ROC surface estimation

Cites work

• scientific article; zbMATH DE number 4001209 (Why is no real title available?)
• Bandwidth selection for kernel distribution function estimation
• Bandwith selection for the smoothing of distribution functions
• Kernel estimators of the ROC curve are better than empirical.
• Local data-driven bandwidth choice for density estimation
• ROC curve estimation based on local smoothing
• Smoothing parameter selection for smooth distribution functions

Cited in

(20)

• Constructing the best linear combination of diagnostic markers via sequential sampling
• Optimal adaptive estimation of the relative density
• Pointwise exact bootstrap distributions of ROC curves
• Sequential estimate of partial area under ROC curve with \(\beta \)-protection and optimal ratio of cases to controls
• Local polynomial fitting of receiver operating characteristic curves
• ROC curves in non-parametric location-scale regression models
• A new method of kernel-smoothing estimation of the ROC curve
• Non-parametric smoothed estimation of multivariate cumulative distribution and survival functions, and receiver operating characteristic curves
• Empirical process approach to some two-sample problems based on ranked set samples
• Comparing diagnostic tests from ROC curve
• Nonparametric estimation of the ROC curve based on smoothed empirical distribution functions
• Relative density estimation for left truncated and right censored data
• Compare diagnostic tests using transformation-invariant smoothed ROC curves
• Modelling receiver operating characteristic curves using Gaussian mixtures
• Minimum distance estimation of the binormal ROC curve
• ROC curves determination by nonparametric methods
• Confidence bands for ROC curves
• Smooth estimation of ROC curve in the presence of auxiliary information
• Nonparametric estimation of conditional ROC curves: application to discrimination tasks in computerized detection of early breast cancer
• Local linear smoothing of receiver operating characteristic (ROC) curves

This page was built for publication: Improved methods for bandwidth selection when estimating ROC curves.

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1423137)