Applications of Long-Memory and Structure Breaks for Carbon Indexes

Abstract

This paper aims to investigatethe long-memory properties of four carbon indexes by utilizing the autoregressive frictionally integrated moving average–fractionally integrated general autoregressive conditional heteroskedasticity models. First, this study discovered a significant long-memory effect for two carbon indexes such as CCX and JOI, whereas others like CER and EUA possess intermediate memory in the returns. Second, the multiple structure breaks in the four carbon indexes were examined using the iterated cumulative sum of squares algorithm. Evidence shows that the sudden shifts are mainly attributed to macroeconomic factors, energy dynamics, and political policies.