×

Nonparametric estimation of the ROC curve based on smoothed empirical distribution functions. (English) Zbl 1322.62122

Summary: The receiver operating characteristic (ROC) curve is a graphical representation of the relationship between false positive and true positive rates. It is a widely used statistical tool for describing the accuracy of a diagnostic test. In this paper we propose a new nonparametric ROC curve estimator based on the smoothed empirical distribution functions. We prove its strong consistency and perform a simulation study to compare it with some other popular nonparametric estimators of the ROC curve. We also apply the proposed method to a real data set.

MSC:

62G05 Nonparametric estimation
62P10 Applications of statistics to biology and medical sciences; meta analysis
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Bamber, D.: The area above the ordinal dominance graph and the area below the receiver operating characteristic graph. J. Math. Psychol. 12, 387–415 (1975) · Zbl 0327.92017 · doi:10.1016/0022-2496(75)90001-2
[2] Bowyer, K., Kranenburg, C., Dougherty, S.: Edge detector evaluation using empirical ROC curves. Comput. Vis. Image Underst. 84(1), 77–103 (2001) · Zbl 1021.68571 · doi:10.1006/cviu.2001.0931
[3] Cai, T., Moskowitz, C.S.: Semi-parametric estimation of the binormal ROC curve for a continuous diagnostic test. Biostatistics 5(4), 573–586 (2004) · Zbl 1069.62087 · doi:10.1093/biostatistics/kxh009
[4] Davidov, O., Nov, Y.: Improving an estimator of Hsieh and Turnbull for the binormal ROC curve. J. Stat. Plan. Inference 142, 872–877 (2012) · Zbl 1428.62471 · doi:10.1016/j.jspi.2011.10.007
[5] Hall, P.G., Hyndmann, R.J.: Improved methods for bandwidth selection when estimating ROC curves. Stat. Probab. Lett. 64, 181–189 (2003) · Zbl 1113.62316 · doi:10.1016/S0167-7152(03)00150-0
[6] Hsieh, F., Turnbull, B.W.: Nonparametric and semiparametric estimation of the receiver operating characteristic curve. Ann. Stat. 24, 25–40 (1996) · Zbl 0855.62029 · doi:10.1214/aos/1033066197
[7] Krzanowski, W.J., Hand, D.J.: ROC Curves for Continuous Data. Chapman and Hall/CRC, London (2009) · Zbl 1288.62005
[8] Lloyd, C.J.: Using smoothed receiver operating characteristic curves to summarize and compare diagnostic systems. J. Am. Stat. Assoc. 93, 1356–1364 (1998) · doi:10.1080/01621459.1998.10473797
[9] Lloyd, C.J., Yong, Z.: Kernel estimators of the ROC curve are better than empirical. Stat. Probab. Lett. 44, 221–228 (1999) · Zbl 1156.62323 · doi:10.1016/S0167-7152(99)00012-7
[10] Pepe, M.S.: An interpretation for the ROC curve and inference using GLM procedures. Biometrics 56, 352–359 (2000) · Zbl 1060.62669 · doi:10.1111/j.0006-341X.2000.00352.x
[11] Pepe, M.S.: The Statistical Evaluation of Medical Tests for Classification and Prediction. Oxford University Press, Oxford (2003) · Zbl 1039.62105
[12] Qin, J., Zhang, B.: Using logistic regression procedures for estimating receiver operating characteristic curves. Biometrika 90, 585–596 (2003) · Zbl 1436.62620 · doi:10.1093/biomet/90.3.585
[13] Tonini, G., Fratto, M.E., Imperatori, M., Pantano, F., Vincenzi, B., Santini, D.: Predictive factors of response to treatment in patients with metastatic renal cell carcinoma: new evidence. Expert Rev. Anticancer Ther. 11(6), 921–930 (2011) · doi:10.1586/era.11.63
[14] Wolfowitz, J.: The minimum distance method. Ann. Math. Stat. 28(1), 75–88 (1957) · Zbl 0086.35403 · doi:10.1214/aoms/1177707038
[15] Zhou, X.H., Harezlak, J.: Comparison of bandwidth selection methods for kernel smoothing of ROC curves. Stat. Med. 21, 2045–2055 (2002) · doi:10.1002/sim.1156
[16] Zhou, X.H., Obuchowski, N.A., McClish, D.K.: Statistical Methods in Diagnostic Medicine. Wiley, New York (2002) · Zbl 1007.62092
[17] Zieliński, R.: Kernel estimators and the Dvoretzky-Kiefer-Wolfowitz inequality. Appl. Math. 34(3), 401–404 (2007) · Zbl 1130.62031
[18] Zou, K.H., Hall, W.J.: Two transformation models for estimating an ROC curve derived from continuous data. J. Appl. Stat. 27(5), 621–631 (2000) · Zbl 0958.62106 · doi:10.1080/02664760050076443
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.