Testing for multiple change-points in macroeconometrics: an empirical guide and recent developments

TL;DR

This paper reviews recent methods for detecting multiple change-points in macroeconomic time series, emphasizing inference on slope parameters and providing practical guidance for empirical macroeconomists.

Contribution

It offers a comprehensive review focused on change-point detection in slope parameters, tailored for macroeconomic applications, highlighting recent developments and practical methods.

Findings

Focus on inference about change-points in slope parameters

Emphasis on detecting multiple change-points using sequential testing

Guidance tailored for empirical macroeconomists

Abstract

We review recent developments in detecting and estimating multiple change-points in time series models with exogenous and endogenous regressors, panel data models, and factor models. This review differs from others in multiple ways: (1) it focuses on inference about the change-points in slope parameters, rather than in the mean of the dependent variable - the latter being common in the statistical literature; (2) it focuses on detecting - via sequential testing and other methods - multiple change-points, and only discusses one change-point when methods for multiple change-points are not available; (3) it is meant as a practitioner's guide for empirical macroeconomists first, and as a result, it focuses only on the methods derived under the most general assumptions relevant to macroeconomic applications.