We illustrate a novel conception of linguistic invariant which applies to grammars of different natural languages even though they may use different categories and have different rules. We illustrate formally how semantically defined notions, such as ?is an anaphor? may be invariant in all linguistically motivated grammars (the issue is an empirical one), and we show that individual morphemes, such as case markers, may be invariant in grammars. One basic fact that we need to keep in mind when discussing differences between American and British grammar is that they are rarely categorical. As a rule, they can be expressed as proportions or probabilities. We might say that, most of the time, American and British speakers have the same grammars, with the same inventory of forms and the same rules, but that the application of the rules differs between varieties. Capturing this variation is the goal of most of the research in this field.