Abstract
Newborn hearing screening with auditory brainstem potentials (ABR) requires objective ABR detection by a statistical test procedure with high performance. Statistical testing can be performed in the time or frequency domain. The aim of the present study was to compare the performance of three tests in the time domain (Friedman test, variance ratio F SP, Cochran's Q-test) with that of a test in the frequency domain (modified q-sample uniform scores test) that, in a former investigation, was shown to be the best test in the frequency domain. To compare the performance of the four tests, the test power was calculated and receiver operating characteristics (ROCs) were constructed from the probability density functions estimated using Monte Carlo simulations. In addition, a comparison on the basis of real near-threshold ABR data was carried out. The modified q-sample uniform scores test appeared to be the most powerful one. Some aspects of practical application are discussed.