chapter  9
16 Pages

Application 7: Testing for Invariant Factorial Structure of Scores from a Measuring Instrument (First-Order CFA Model)

In contrast to the example provided in chapter 8, the present application focuses on tests for invariance related to a single measuring instrument, the Self Description Questionnaire III (SDQ-III, Marsh, 1992b). Specifically, we explore the factorial equivalence of the SDQ-III across two academically tracked Qow and high) groups of high school students. {For details related to the sample, and other aspects of the study, readers are referred to the original publication, (see, Byrne, 1988c); for a more extensive discussion of academic tracking, as it relates to the data used in the present example, see Byrne, 1988a; and for detailed description and evaluation of the SDQ-III, see Byrne, 1996.)

Typically, in testing for the factorial invariance of a single measuring instrument, the researcher has two primary concerns: (a) the extent to which the items comprising each subscale are factorially valid and their content equivalently interpreted across groups, and (b) the extent to which the structural relations among the factors (i.e., the factor covariances) are equivalent across groups. In addition, however, it may be of interest to test the extent to which the sub scale items are equally reliable across groups. This chapter addresses each of these issues.