Correcting for verification bias in studies of a diagnostic test's accuracy
- 1 August 1998
- journal article
- review article
- Published by SAGE Publications in Statistical Methods in Medical Research
- Vol. 7 (4) , 337-353
- https://doi.org/10.1177/096228029800700403
Abstract
Standard methods for assessing the accuracy of diagnostic tests require determination of true disease status for each study patient. In practice, some study patients might not have verified disease status. If the decision to verify a patient is influenced by the test result, analysis using only verified cases might lead to biased results, commonly known as verification bias. This paper reviews recent developments in bias-correction methods for studies on the accuracy of diagnostic tests.Keywords
This publication has 33 references indexed in Scilit:
- The Generalized Estimating Equation Approach When Data are Not Missing Completely at RandomJournal of the American Statistical Association, 1997
- ORDINAL REGRESSION METHODOLOGY FOR ROC CURVES DERIVED FROM CORRELATED DATAStatistics in Medicine, 1996
- Estimation of Regression Coefficients When Some Regressors are not Always ObservedJournal of the American Statistical Association, 1994
- Maximum likelihood estimators of sensitivity and specificity corrected for verification biasCommunications in Statistics - Theory and Methods, 1993
- An Exponential Model Used for optimal Threshold selection on ROC CuruesMedical Decision Making, 1988
- Sensitivity and specificity of tests: Can the “silent majority” speak?The American Journal of Cardiology, 1987
- ROC Methodology in Radiologic ImagingInvestigative Radiology, 1986
- Longitudinal data analysis using generalized linear modelsBiometrika, 1986
- Methodologic problems of exercise testing for coronary artery disease: Groups, analysis and biasThe American Journal of Cardiology, 1980
- Problems of Spectrum and Bias in Evaluating the Efficacy of Diagnostic TestsNew England Journal of Medicine, 1978