Refined distributional limit theorems for compound sums

The paper is a sketch of systematic presentation of distributional limit theorems and their refinements for compound sums. When analyzing, e.g., ergodic semi-Markov systems with discrete or continuous time, this allows us to separate those aspects that lie within the theory of random processes from those that relate to the classical summation theory. All these limit theorems are united by a common approach to their proof, based on the total probability rule, auxiliary multidimensional limit theorems for sums of independent random vectors, and (optionally) modular analysis.