Moving sum procedure for multiple change point detection in large factor models

TL;DR

This paper introduces a moving sum approach for detecting multiple change points in high-dimensional factor models, effectively identifying changes in loadings and factors with proven statistical properties and strong empirical performance.

Contribution

It develops a novel moving sum methodology with proven asymptotic null distribution and consistency for multiple change point detection in large factor models.

Findings

Method controls family-wise error rate.

Consistent detection of multiple change points.

Demonstrates strong performance on real volatility data.

Abstract

This paper proposes a moving sum methodology for detecting multiple change points in high-dimensional time series under a factor model, where changes are attributed to those in loadings as well as emergence or disappearance of factors. We establish the asymptotic null distribution of the proposed test for family-wise error control, and show the consistency of the procedure for multiple change point estimation. Simulation studies and an application to a large dataset of volatilities demonstrate the competitive performance of the proposed method.