Stability of Meanings versus Rate of Replacement of Words: An Experimental Test

The words of a language are randomly replaced over time by new ones, but it has long been known that words corresponding to some items (meanings) are less frequently replaced than others. Usually, the rate of replacement for a given item is not directly observable, but it is inferred by the estimated stability which, on the contrary, is observable. This strategy goes back a long way in the lexicostatistical literature, nevertheless nothing ensures that it gives the correct answer. The family of Romance languages allows for a direct test of the estimated stabilities against the replacement rates since the proto-language (Late Classical Latin or Vulgar Latin) is more or less known, and the replacement rates can be explicitly computed. The output of the test is threefold: i) we prove that the standard approach which infers the replacement rates through the estimated stabilities is sound; ii) we are able to rewrite the fundamental formula of Glottochronology for a non universal replacement rate (depending on the item); iii) we provide unquestionable evidence that the stability ranking is far from being the same for different families of languages. This last result is also supported by comparison with the Malagasy family of dialects.