The comparison of scores from linguistically different tests is a twofold matter: the adaptation of tests and the comparison of scores. These 2 aspects of measurement invariance intersect at the need to guarantee the psychometric equivalence between the original and adapted versions. In this study, the authors examined comparability in 2 stages. First, they conducted a thorough study of progressive factorial variance through which they defined an anchor test. Second, they defined an observed score-equated function to establish equivalences between the original test and the adapted test; they used a design of common item nonequivalent groups for this purpose. (Contains 4 tables, 3 figures, and 1 note.)