Bayesian bootstrap estimation of ROC curve

被引:39
|
作者
Gu, Jiezhun [1 ]
Ghosal, Subhashis [2 ]
Roy, Anindya [3 ]
机构
[1] Duke Univ, Med Ctr, Duke Clin Res Inst, Durham, NC 27715 USA
[2] N Carolina State Univ, Dept Stat, Raleigh, NC 27695 USA
[3] Univ Maryland, Dept Math & Stat, Baltimore, MD 21201 USA
关键词
area under the curve (AUC); Bayesian bootstrap; integrated absolute error; ROC Curve; testing binormality;
D O I
10.1002/sim.3366
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
Receiver operating characteristic (ROC) Curve is widely applied in measuring discriminatory ability of diagnostic or prognostic tests. This makes the ROC analysis one of the most active research areas in medical statistics. Many parametric and semiparametric estimation methods have been proposed for estimating the ROC curve and its functionals. In this paper, we propose the Bayesian bootstrap (BB), a fully nonparametric estimation method, for the ROC curve and its functionals, such as the area under the curve (AUC). The BB method offers a bandwidth-free smoothing approach to the empirical estimate, and gives credible bounds. The accuracy of the estimate of the ROC curve in the simulation studies is examined by the integrated absolute error. In comparison with other existing curve estimation methods, the BB method performs well in terms of accuracy, robustness and simplicity. We also propose a procedure based on the BB approach to test the binormality assumption. Copyright (C) 2008 John Wiley & Sons, Ltd.
引用
收藏
页码:5407 / 5420
页数:14
相关论文
共 50 条
  • [1] Bayesian ROC curve estimation under verification bias
    Gu, Jiezhun
    Ghosal, Subhashis
    Kleiner, David E.
    [J]. STATISTICS IN MEDICINE, 2014, 33 (29) : 5081 - 5096
  • [2] Bayesian semiparametric ROC curve estimation and disease diagnosis
    Branscum, Adam J.
    Johnson, Wesley O.
    Hanson, Timothy E.
    Gardner, Ian A.
    [J]. STATISTICS IN MEDICINE, 2008, 27 (13) : 2474 - 2496
  • [3] Bayesian ROC curve estimation under binormality using a rank likelihood
    Gu, Jiezhun
    Ghosal, Subhashis
    [J]. JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 2009, 139 (06) : 2076 - 2083
  • [4] Bayesian ROC curve estimation under binormality using an ordinal category likelihood
    Wang, Xiaoguang
    Niu, Yi
    Li, Xiaofang
    [J]. COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 2018, 47 (18) : 4628 - 4640
  • [5] Exact bootstrap variances of the area under ROC curve
    Bandos, Andriy I.
    Rockette, Howard E.
    Gur, David
    [J]. COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 2007, 36 (13-16) : 2443 - 2461
  • [6] Estimation of a convex ROC curve
    Lloyd, CJ
    [J]. STATISTICS & PROBABILITY LETTERS, 2002, 59 (01) : 99 - 111
  • [7] ROC CURVE ESTIMATION: AN OVERVIEW
    Goncalves, Luzia
    Subtil, Ana
    Rosario Oliveira, M.
    Bermudez, Patricia De Zea
    [J]. REVSTAT-STATISTICAL JOURNAL, 2014, 12 (01) : 1 - 20
  • [8] Web-Bootstrap Estimate of Area Under ROC Curve
    Skalska, Hana
    Freylich, Vaclav
    [J]. AUSTRIAN JOURNAL OF STATISTICS, 2006, 35 (2-3) : 325 - 330
  • [9] Bootstrap estimated true and false positive rates and ROC curve
    Adler, Werner
    Lausen, Berthold
    [J]. COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2009, 53 (03) : 718 - 729
  • [10] Cumulative/dynamic ROC curve estimation
    Martinez-Camblor, Pablo
    Bayon, Gustavo F.
    Perez-Fernandez, Sonia
    [J]. JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION, 2016, 86 (17) : 3582 - 3594