×

Improved methods for bandwidth selection when estimating ROC curves. (English) Zbl 1113.62316

Summary: The receiver operating characteristic (ROC) curve is used to describe the performance of a diagnostic test which classifies observations into two groups. We introduce new methods for selecting bandwidths when computing kernel estimates of ROC curves. Our techniques allow for interaction between the distributions of each group of observations and give substantial improvement in MISE over other proposed methods, especially when the two distributions are very different.

MSC:

62G07 Density estimation
Full Text: DOI

References:

[1] Altman, N.; Léger, C., Bandwidth selection for kernel distribution function estimation, J. Statist. Plann. Inference, 46, 195-214 (1995) · Zbl 0833.62035
[2] Azzalini, A., A note on the estimation of a distribution function and quantiles by a kernel method, Biometrika, 68, 326-328 (1981)
[3] Bowman, A. W.; Hall, P.; Prvan, T., Cross-validation for the smoothing of distribution functions, Biometrika, 85, 799-808 (1998) · Zbl 0921.62042
[4] Lloyd, C. J., The use of smoothed ROC curves to summarise and compare diagnostic systems, J. Amer. Statist. Assoc., 93, 1356-1364 (1998)
[5] Lloyd, C. J.; Yong, Z., Kernel estimators of the ROC curve are better than empirical, Statist. Probab. Lett., 44, 221-228 (1999) · Zbl 1156.62323
[6] Mielniczuk, J.; Sarda, P.; Vieu, P., Local data-driven bandwidth choice for density estimation, J. Statist. Plann. Inference, 23, 53-69 (1989) · Zbl 0689.62027
[7] Peng, L., Zhou, X.-H., 2003. Local linear smoothing of receiver operator characteristic (ROC) curves. J. Statist. Plann. Inference, in press.; Peng, L., Zhou, X.-H., 2003. Local linear smoothing of receiver operator characteristic (ROC) curves. J. Statist. Plann. Inference, in press.
[8] Qiu, P.; Le, C., ROC curve estimation based on local smoothing, J. Statist. Comput. Simulation, 70, 55-69 (2001) · Zbl 0985.62030
[9] Sarda, P., Smoothing parameter selection for smooth distribution functions, J. Statist. Plann. Inference, 35, 65-75 (1993) · Zbl 0769.62030
[10] Silverman, B. W., Density Estimation for Statistics and Data Analysis (1986), Chapman & Hall: Chapman & Hall London · Zbl 0617.62042
[11] Zou, K. H.; Hall, W. J.; Shapiro, D. E., Smooth non-parametric receiver operating characteristic (ROC) curves for continuous diagnostic tests, Statist. Med., 16, 2143-2156 (1997)
[12] Zhou, X.-H.; Harezlak, J., Comparison of bandwidth selection methods for kernel smoothing of ROC curves, Statist. Med., 21, 2045-2055 (2002)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.