Detection of differential item functioning (DIF) is most often done between two groups of examinees under item response theory. It is sometimes important, however, to determine whether DIF is present in more than two groups. A method is presented for the detection of DIF in multiple groups. The method, the Q(sub j) statistic, is closely related to the chi-square method of F. M. Lord for comparing vectors of item parameters estimated in two groups and is based on the same assumptions. An example is provided using real data from 3 groups of 200 college students each (1 reference and 2 focal groups). Five tables present analysis results, and a 49-item list of references is included. (Author/SLD)