: The area under the receiver operating characteristic (ROC) curve (AUC) is a popularly used index when comparing two ROC curves. However, this index is less informative when two ROC curves cross while the AUCs are the same. In order to detect differences between ROC curves and to be able to tackle the problem of transformation of the original data and exchangeability of the labels of two diagnostic tests within subject which characterized the methods proposed by Venkatraman and Beggs (1996) as well as Bandos et al(2005), an alternative permutation test based on between-subject permutations of the labels of the subjects is proposed for assessing a change in the AUCs in a matched pair of data from two diagnostic test procedures having both diseased and nondiseased subject in each of the test. Here permutations are made between subjects particularly by shuffling the diseased and nondiseased labels of the subjects within each diagnostic test procedure. The validity of this permutation test is assured even when the scale of measurement of test results differs for each diagnostic test procedure. We demonstrate under the assumption of equality of AUCs that our permutation test is a modified Wilcoxon signed rank test for the symmetry of an underlying discrete distribution with valid sample size. Through extensive data simulation, we show the numerical studies of operating characteristics of our new permutation test and show that our test has equal statistical power to a permutation test proposed by Bandos et al(2005).