Multiple change-points estimation in panel data models via SaRa

Abstract

Multiple change-points estimation in panel data models is one of the popular topics in statistics. In this article, we investigate the multiple change-points estimation in the mean of panel data model based on a screening and ranking algorithm. Firstly, the possible change-points are initially screened based on local statistics. Secondly, the threshold is used to further screen the change-points. Finally, the final change-points are screened out using the information criterion. Furthermore, the consistency of the change-point estimators is proved. The Monte Carlo simulation results show that the proposed method can estimate the number and locations of change-points accurately even if the error terms are serially correlated or cross-sectionally correlated, and finally the method is used to analyze the annual GDP growth rate data of 47 countries in the word from 1971 to 2019 to illustrate the effectiveness of the method.