In this paper, we explore the possibilities of structural breaks in the realized volatility with the observed long-memory property for the Deutschemark/Dollar, Yen/Dollar and Yen/Deutschemark spot exchange rate realized volatility. The paper finds the substantial reduction of persistence of realized volatility after removing the breaks. Our VAR-RV-Break model provides the superior predictive ability compared to most of the forecasting models when the future break is known. The VAR-RV-I(d) long memory model, however, is still the best forecasting model even when the true financial volatility series are created by structural breaks with unknown break dates and size.
Yu, Wei-Choun; Choi, Kyongwook; and Zivot, Eric, "Long Memory versus Structural Breaks in Modeling and Forecasting Realized Volatility" (2006). Economics Seminar Series. 6.