View in EDS

Confidence Intervals for AUC and pAUC by Empirical Likelihood.

Saved in:
Bibliographic Details
Title: Confidence Intervals for AUC and pAUC by Empirical Likelihood.
Authors: Zhao Y; Eli Lilly and Company, Indianapolis, Indiana, USA., Ding X; Dr. Bing Zhang Department of Statistics, University of Kentucky, Lexington, Kentucky, USA., Zhou M; Dr. Bing Zhang Department of Statistics, University of Kentucky, Lexington, Kentucky, USA.
Source: Statistics in medicine [Stat Med] 2025 Jul; Vol. 44 (15-17), pp. e70192.
Publication Type: Journal Article
Language: English
Journal Info: Publisher: Wiley Country of Publication: England NLM ID: 8215016 Publication Model: Print Cited Medium: Internet ISSN: 1097-0258 (Electronic) Linking ISSN: 02776715 NLM ISO Abbreviation: Stat Med Subsets: MEDLINE
Imprint Name(s): Original Publication: Chichester ; New York : Wiley, c1982-
MeSH Terms: Area Under Curve* , ROC Curve* , Diagnostic Tests, Routine*/statistics & numerical data, Likelihood Functions ; Humans ; Confidence Intervals ; Computer Simulation ; Models, Statistical ; Statistics, Nonparametric
Abstract: The area under the receiver operating characteristic curve (AUC) and Partial AUC (pAUC) are often used to measure the performance of medical diagnostic tests. Under nonparametric settings, we propose and illustrate in this paper a two-sample empirical likelihood approach to test hypotheses and construct confidence intervals for AUC and pAUC. The empirical likelihood ratio test in our setup yields an asymptotic chi-square distribution under null hypothesis. Thus, there is no need to estimate the complicated scale factor or the variance of the nonparametric AUC/pAUC estimators like most other competing methods do. Simulations show our method is very competitive. In fact, our method tops competitors in every situation we simulated. Real data examples (with R code) are presented illustrating the statistical tests and confidence intervals for AUC and pAUC.
(© 2025 John Wiley & Sons Ltd.)
References: T. Yang and Y. Ying, “AUC Maximization in the Era of Big Data and AI: A Survey,” ACM Computing Surveys 55 (2022): 1–37, https://doi.org/10.1145/3554729.
M. Pepe, The Statistical Evaluation of Medical Tests for Classification and Prediction (Oxford University Press, 2003).
X. Zhou, N. Obuchowski, and D. McClish, Statistical Methods in Diagnostic Medicine, 2nd ed. (John Wiley & Sons, 2011).
K. Zou, A. Liu, A. Bandos, L. Ohno‐Machado, and H. Rockette, Statistical Evaluation of Diagnostic Performance: Topics in ROC Analysis (Chapman & Hall/CRC, 2012).
W. Krzanowski and D. Hand, ROC Curves for Continuous Data (Chapman & Hall/CRC, 2009).
X. Robin, N. Turck, A. Hainard, et al., “pROC: An Open‐Source Package for R and S+ to Analyze and Compare ROC Curves,” BMC Bioinformatics 12, no. 77 (2011), https://doi.org/10.1186/1471‐2105‐12‐77.
J. Hanley and B. McNeil, “The Meaning and Use of the Area Under a Receiver Operating Characteristic (ROC) Curve,” Radiology 143 (1982): 29–36.
L. Dodd and M. Pepe, “Partial AUC Estimation and Regression,” Biometrics 59 (2003): 614–623.
A. Owen, Empirical Likelihood (Chapman & Hall/CRC, 2001).
D. O'Brien, N. Sandanayake, C. Jenkinson, et al., “Serum CA19‐9 Is Significantly Up‐Regulated Up to 2 Years Prior to Diagnosis With Pancreatic Cancer: Implications for Early Disease Detection,” Clinical Cancer Research 21 (2015): 622–96631.
S. Modi, D. Kir, and A. Saluja, “Old Dog, New Tricks: Use of CA 19–9 for Early Diagnosis of Pancreatic Cancer,” Gastroenterology 160, no. 4 (2021): 1019–1021, https://doi.org/10.1053/j.gastro.2021.01.001.
H. Wieand, M. Gail, and B. James, “A Family of Nonparametric Statistics for Comparing Diagnostic Markers With Paired or Unpaired Data,” Biometrika 76 (1989): 585–592.
M. Zhou, X. Ding, and Y. Zhao, “Empirical Likelihood Ratio Test/Confidence Interval for AUC or pAUC,” R Foundation for Statistical Computing (2024), https://CRAN.R‐project.org/package=emplikAUC.
D. McClish, “Analyzing a Portion of the ROC Curve,” Medical Decision Making 9, no. 3 (1989): 190–195.
S. Chen and P. Hall, “Smoothed Empirical Likelihood Confidence Intervals for Quantiles,” Annals of Statistics 21 (1993): 1166–1181.
K. Zou, W. Hall, and D. Shapiro, “Smooth Non‐Parametric Receiver Operating Characteristic (ROC) Curves for Continuous Diagnostic Tests,” Statistics in Medicine 16 (1997): 2143–2156.
H. Yang, K. Lu, and Y. Zhao, “A Nonparametric Approach for Partial Areas Under Roc Curves and Ordinal Dominance Curves,” Statistica Sinica 27 (2017): 357–371.
J. Qin and J. Lawless, “Empirical Likelihood and General Estimating Equations,” Annals of Statistics 22 (1994): 300–325.
N. Turck, L. Vutskits, P. Sanchez‐Pena, et al., “A Multiparameter Panel Method for Outcome Prediction Following Aneurysmal Subarachnoid Hemorrhage,” Intensive Care Medicine 36 (2010): 107–115.
M. Zhou, “A Novel Alternative Estimator of pAUC Turns Out to be the Same Good old one. Technical Report, University of Kentucky; Lexington, KY,” 2024, https://www.ms.uky.edu/∼mai/research/SSshort.pdf.
E. DeLong, D. DeLong, and D. Clarke‐Pearson, “Comparing the Area Under Two or More Correlated Receiver Operating Characteristic Curves: A Nonparametric Approach,” Biometrics 44 (1988): 837–845.
D. Feng, G. Cortese, and R. Baumgartner, “A Comparison of Confidence/Credible Interval Methods for the Area Under the ROC Curve for Continuous Diagnostic Tests With Small Sample Size,” Statistical Methods in Medical Research 26, no. 6 (2017): 2603–2621.
B. Efron and R. J. Tibshirani, An Introduction to the Bootstrap. No. 57 in Monographs on Statistics and Applied Probability (Chapman & Hall/CRC, 1993).
G. Qin, X. Jin, and X. Zhou, “Non‐Parametric Interval Estimation for the Partial Area Under the ROC Curve,” Canadian Journal of Statistics 39, no. 1 (2011): 17–33.
G. Qin and X. Zhou, “Empirical Likelihood Inference for the Area Under the ROC Curve,” Biometrics 62, no. 2 (2006): 613–622.
N. Hjort, I. McKeague, and I. Keilegom, “Extending the Scope of Empirical Likelihood,” Annals of Statistics 37 (2009): 1079–1111.
G. Adimari and M. Chiogna, “Jackknife Empirical Likelihood Based Confidence Intervals for Partial Areas Under ROC Curves,” Statistica Sinica 22 (2012): 1457–1477.
J. Yu, L. Yang, A. Vexler, and A. Hutson, “Easy and Accurate Variance Estimation of the Nonparametric Estimator of the Partial Area Under the ROC Curve and Its Application,” Statistics in Medicine 35, no. 13 (2016): 2251–2282.
P. Gaver and R. Miller, “Jackknifing the Kaplan‐Meier Survival Estimator for Censored Data: Simulation Results and Asymptotic Analysis,” Communications in Statistics 12 (1983): 1701–1718.
B. Jing, J. Yuan, and W. Zhou, “Jackknife Empirical Likelihood,” Journal of the American Statistical Association 104 (2009): 1224–1232.
M. Zhou, Empirical Likelihood Method in Survival Analysis (Chapman & Hall/CRC, 2016).
W. Meeker and L. Escobar, “Teaching About Approximate Confidence Regions Based on Maximum Likelihood Estimation,” American Statistician 49, no. 1 (1995): 48–53.
M. Kim and M. Zhou, “Comparison of Extended Empirical Likelihood Methods: Size and Shape of Test‐Based Confidence Regions,” Statistica Sinica 29 (2019): 371–386.
Contributed Indexing: Keywords: ROC curve; chi‐square distribution; nuisance parameter; partial AUC; two‐sample empirical likelihood; wilks confidence intervals
Entry Date(s): Date Created: 20250721 Date Completed: 20250721 Latest Revision: 20250721
Update Code: 20250721
DOI: 10.1002/sim.70192
PMID: 40689495
Database: MEDLINE
Description
Abstract:The area under the receiver operating characteristic curve (AUC) and Partial AUC (pAUC) are often used to measure the performance of medical diagnostic tests. Under nonparametric settings, we propose and illustrate in this paper a two-sample empirical likelihood approach to test hypotheses and construct confidence intervals for AUC and pAUC. The empirical likelihood ratio test in our setup yields an asymptotic chi-square distribution under null hypothesis. Thus, there is no need to estimate the complicated scale factor or the variance of the nonparametric AUC/pAUC estimators like most other competing methods do. Simulations show our method is very competitive. In fact, our method tops competitors in every situation we simulated. Real data examples (with R code) are presented illustrating the statistical tests and confidence intervals for AUC and pAUC.<br /> (© 2025 John Wiley & Sons Ltd.)
ISSN:1097-0258
DOI:10.1002/sim.70192