Estimation of Sensitivity and Specificity for Clustered Data


Abstract: The most commonly used measurements for evaluating the accuracy of diagnostic tests in binary data are sensitivity and specificity. Sensitivity refers to the ability of a test to detect patients with some specific disease. Specificity describes how well test abnormality is restricted to those persons who have the disease in question. The variance estimators of these measurements are usually obtained using a binomial estimator, although there are several other methods. However, under certain conditions more than one observation can be taken from a subject and analyses are performed on these observations. This type of data structure is called "clustered data". For calculating sensitivity, specificity and related variances in clustered data, conventional statistical methods with the assumption that all observations are independent will not be valid. The most commonly used methods for clustered data are "ratio estimator", "within-cluster correlation estimator" and "weighted estimator". In this paper, for calculating diagnostic measurements and their variances, the above-mentioned methods are described. In the example of magnetic resonance angiography, which is used for the diagnosis of renal artery stenosis, the results of a binomial estimator are compared with those of the other 3 methods. Although there were no significant differences between sensitivity estimates, variance estimates obtained from the binomial estimator were higher than the other estimates.

Keywords: Sensitivity, Specificity, Clustered data

Full Text: PDF