ABSTRACT
This study suggests a structural modification of the basic ARFIMA-GARCH model by allowing for time-varying baseline mean and, especially, symmetric threshold GARCH. By applying it to the inflation of G7 countries, we find that past excessive positive or negative shocks have positive impacts on future volatility and GARCH persistence. Compared with the ARFIMA-GARCH model, the model in this study has superior performances in identifying and characterizing structural changes and excessive shocks.
Acknowledgments
We would like to show our great appreciation to two referees, as well as Professor David Peel, Co-Editor of Applied Economics Letters, whose comments and suggestions greatly improved the quality of this paper.
Disclosure statement
No potential conflict of interest was reported by the authors.