The Monotone Cumulants

TL;DR

This paper introduces generalized cumulants applicable across various probability theories, including monotone, providing a new, partition-free perspective and simplifying proofs of key limit theorems.

Contribution

It defines a universal framework for cumulants that applies to multiple probability theories, especially introducing monotone cumulants without relying on partition lattices.

Findings

Unified framework for cumulants across different theories

Simplified proofs of central limit theorem and Poisson law in monotone probability

Clarification of combinatorial structure via monotone partitions

Abstract

In the present paper we define the notion of generalized cumulants which gives a universal framework for commutative, free, Boolean, and especially, monotone probability theories. The uniqueness of generalized cumulants holds for each independence, and hence, generalized cumulants are equal to the usual cumulants in the commutative, free and Boolean cases. The way we define (generalized) cumulants needs neither partition lattices nor generating functions and then will give a new viewpoint to cumulants. We define ``monotone cumulants'' in the sense of generalized cumulants and we obtain quite simple proofs of central limit theorem and Poisson's law of small numbers in monotone probability theory. Moreover, we clarify a combinatorial structure of moment-cumulant formula with the use of ``monotone partitions''.