In many clinical experiments it is clear that external factors can aff
ect the performance of diagnostic tests as these factors influence the
distributions of separator variables. The authors investigate how str
atification of cases and/or controls can be used in nonparametric rece
iver operating characteristic (ROC) studies, and develop statistical m
ethods using stratification. The method can be used to simultaneously
assess the ability of a diagnostic marker against several types of con
trols or cases. This allows a new method for the assessment of diagnos
tic tests.