A Framework for Asymptotic Limit Problems of Probabilistic Nature

Abstract

A convenient framework for dealing with asymptotic limit problems of probabilistic nature is provided. These problems include questions such as finding the asymptotic proportion of terms of a sequence falling inside a given interval, or the limit of the arithmetic mean of its partial sums; but several classes of problems are examined in a much more general setting. The proposed framework, which aims to unify those questions and their solution, is based on the idea that to any finite multiset $E_n$, one can associate a finitely distributed atomic probability $\mu_n$; assuming $\mu_n$ tends in distribution to a probability $\mu$, it provides the tools needed to establish the desired asymptotic limit. Few examples are worked out in order to illustrate how using the framework.