Change Point Detection in Correlation Networks

TL;DR

This paper introduces a new method for detecting change points in evolving correlation networks without relying on distributional assumptions, demonstrated through simulations and real-world data applications.

Contribution

The paper presents a novel change point detection technique tailored for correlation networks that works without distributional assumptions, applicable to various data types.

Findings

Method effectively detects change points in correlation networks.

Demonstrates robustness near data boundaries.

Applicable to stock prices and fMRI data.

Abstract

Many systems of interacting elements can be conceptualized as networks, where network nodes represent the elements and network ties represent interactions between the elements. In systems where the underlying network evolves in time, it is useful to determine the points in time where the network structure changes significantly as these may correspond also to functional change points. We propose a method for detecting these change points in correlation networks that, unlike previous change point detection methods designed for time series data, requires no distributional assumptions. We investigate the difficulty of change point detection near the boundaries of data in correlation networks and demonstrate the power of our method and a competing method through simulation. We also show the generalizable nature of our method by applying it to stock price data as well as fMRI data.