Positive assortative matching refers to the tendency of individuals with similar characteristics to form partnerships. Measuring the extent to which assortative matching differs between two economies is challenging when the marginal distributions of the sorting characteristic (e.g., education) change for either or both sexes. We show how the use of different measures can generate different conclusions. We provide an axiomatic characterization for the odds ratio, normalized trace, and likelihood ratio and provide a structural economic interpretation of the odds ratio. We use our approach to show that marital sorting by education substantially changed between the 1950s and the 1970s cohorts.