Frequent or Systematic Changes? discussion on "Detecting possibly frequent change-points: Wild Binary Segmentation 2 and steepest-drop model selection."

TL;DR

This paper critically examines Fryzlewicz's WBS2.SDLL method for detecting frequent change-points, highlighting potential issues with model misspecification through numerical examples like autoregression and unit root processes.

Contribution

It provides a discussion on the limitations of WBS2.SDLL in the presence of model misspecification and illustrates potential confusions with other time series models.

Findings

WBS2.SDLL may be confused with models like autoregression and unit root processes.

Model misspecification can lead to false detection of frequent change-points.

Numerical examples demonstrate potential pitfalls of the method.

Abstract

We discuss Fryzlewicz's (2020) that proposes WBS2.SDLL approach to detect possibly frequent changes in mean of a series. Our focus is on the potential issues related to the model misspecification. We present some numerical examples such as the self-exciting threshold autoregression and the unit root process, that can be confused as a frequent change-points model.