Comparing diagnostic tests: test of hypothesis for likelihood ratios. (English) Zbl 1431.62494
Summary: Likelihood ratios (LRs) are used to characterize the efficiency of diagnostic tests. In this paper, we use the classical weighted least squares (CWLS) test procedure, which was originally used for testing the homogeneity of relative risks, for comparing the LRs of two or more binary diagnostic tests. We compare the performance of this method with the relative diagnostic likelihood ratio (rDLR) method and the diagnostic likelihood ratio regression (DLRReg) approach in terms of size and power, and we observe that the performances of CWLS and rDLR are the same when used to compare two diagnostic tests, while DLRReg method has higher type I error rates and powers. We also examine the performances of the CWLS and DLRReg methods for comparing three diagnostic tests in various sample size and prevalence combinations. On the basis of Monte Carlo simulations, we conclude that all of the tests are generally conservative and have low power, especially in settings of small sample size and low prevalence.
MSC:
| 62P10 | Applications of statistics to biology and medical sciences; meta analysis |
| 62J20 | Diagnostics, and linear inference and regression |
Keywords:
binary diagnostic tests; comparing likelihood ratios; classical weighted least squares; relative diagnostic likelihood ratio; diagnostic likelihood ratio regression; type I error; statistical power; statistical simulationSoftware:
StataReferences:
| [1] | Zweig M. H., Clin. Chem. 39 pp 561– (1993) |
| [2] | Pepe M. S., The Statistical Evaluation of Medical Tests for Classification and Prediction (2003) · Zbl 1039.62105 |
| [3] | Zhou X. H., Statistical Methods in Diagnostic Medicine (2002) · Zbl 1007.62092 · doi:10.1002/9780470317082 |
| [4] | Fletcher R. H., Clinical Epidemiology. The Essentials (1996) |
| [5] | Jaeschke R., J. Am. Med. Assoc. 271 pp 703– (1994) · doi:10.1001/jama.1994.03510330081039 |
| [6] | Biggerstaff B. J., Stat. Med. 19 pp 649– (2000) · doi:10.1002/(SICI)1097-0258(20000315)19:5<649::AID-SIM371>3.0.CO;2-H |
| [7] | Simel D. L., J. Clin. Epidemiol. 44 pp 763– (1991) · doi:10.1016/0895-4356(91)90128-V |
| [8] | Leisenring W., Biometrics 54 pp 444– (1998) · Zbl 1058.62622 · doi:10.2307/3109754 |
| [9] | Nofuentes J. A.R., Stat. Med. 26 pp 4179– (2007) · doi:10.1002/sim.2850 |
| [10] | Fleiss J. L., Statistical Methods for Rates and Proportions (1981) · Zbl 0544.62002 |
| [11] | Lachin J. M., Biostatistical Methods: The Assessment of Relative Risks (2000) · Zbl 0961.62096 · doi:10.1002/9780470317051 |
| [12] | Agresti A., Categorical Data Analysis (1990) · Zbl 0716.62001 |
| [13] | Dressler F., J. Infect. Dis. 167 pp 392– (1993) · doi:10.1093/infdis/167.2.392 |
| [14] | Johnson B. J.B., J. Infect. Dis. 174 pp 346– (1996) · doi:10.1093/infdis/174.2.346 |
| [15] | Leisenring W., Downloadable stata programs and help files for diagnostic likelihood ratio regression (lrreg.ado lrreg_ll.ado lrreg.hlp) in the webpage for The Statistical Evaluation of Medical Tests for Classification and Prediction (2003) |
| [16] | Lui K.-J., Stat. Med. 19 pp 2919– (2000) · doi:10.1002/1097-0258(20001115)19:21<2919::AID-SIM561>3.0.CO;2-D |
| [17] | Lui K.-J., Biom. J. 48 pp 131– (2006) · doi:10.1002/bimj.200410193 |
| [18] | Glas A. S., J. Clin. Epidemiol. 56 pp 1129– (2003) · doi:10.1016/S0895-4356(03)00177-X |
| [19] | Mulherin S. A., Ann. Intern. Med. 137 pp 598– (2002) · doi:10.7326/0003-4819-137-7-200210010-00011 |
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.
