Volatility Jump of Multi-Power and Maximum Outlyingness with Periodicity Filters in China yuan/US dollar Exchange Rates

Abstract

The discrete daily and intraday jump probabilities of China yuan/US dollar returns from June 1, 2012 to April 30, 2021 is analyzed using five-minute returns considering periodicity filters of volatility. When we use Z-daily jump using either tripower quarticity and quadpower quarticity, the daily jump probability seems to be 66% and 70%, respectively, at α = 0.999. Thus, if the periodicity filters of volatility are not considered, the jump probabilities may be overestimated. When we use the intraday observations or periods, with the periodicity filters of volatility such as such as MAD and short half scale, the daily jump probability seems to be 39% and 40% at α = 0.999, respectively. When we consider the periodicity filters of volatility, the five-minute returns of China yuan/US dollar exchange rates have considerably lower daily jump probabilities than we use using max outlying daily jump statistics without MAD periodicity filters of volatility.