Abstract
We conduct an extensive evaluation of price jump tests based on high-frequency financial data. After providing a concise review of multiple alternative tests, we document the size and power of all tests in a range of empirically relevant scenarios. Particular focus is given to the robustness of test performance to the presence of jumps in volatility and microstructure noise, and to the impact of sampling frequency. The paper concludes by providing guidelines for empirical researchers about which test to choose in any given setting.
Highlights
Extreme movements in asset prices play an important role in the tail behaviour of return distributions, with the perceived risk associated with this extreme behaviour differing from that associated with small and regular movements
Evidence of price jump clustering in spot returns - whereby price and/or volatility jumps occur in consecutive time periods - has been uncovered, with various approaches having been adopted to model this dynamic behaviour, including the use of simultaneous price and volatility jumps over time
Multiple alternative methods are available to practitioners, both for testing for jumps and for measuring price variation in the presence of jumps, with some empirical analyses exploiting such measures in addition to, or as a replacement of, measurements based on end-of-day prices. (See Koopman and Scharth, 2013, Christensen et al, 2014, and Maneesoonthorn et al, 2017, for recent examples, including references to earlier work.)
Summary
Extreme movements (or ‘jumps’) in asset prices play an important role in the tail behaviour of return distributions, with the perceived risk (and, risk premium) associated with this extreme behaviour differing from that associated with small and regular movements (see, Bates, 1996, and Duffie et al, 2000, for early illustrations of this point, and Todorov and Tauchen, 2011, Maneesoonthorn et al, 2012, and Bandi and Reno, 2016, for more recent expositions). These methods are grouped into five categories: 1) those based on the difference between a measure of total (squared) variation and a jump-robust measure of integrated variation (Barndorff-Nielsen and Shephard, 2004, 2006; Huang and Tauchen, 2005; Corsi et al, 2010; Andersen et al, 2012); 2) those that exploit measures of higher-order variation (Aıt-Sahalia and Jacod, 2009; Podolskij and Ziggel, 2010); 3) those based on returns, rather than measures of variation (Andersen et al, 2007; Lee and Mykland, 2008); 4) those that exploit a variance swap (Jiang and Oomen, 2008); and 5) those that are expressly designed to mitigate the impact of microstructure noise (Aıt-Sahalia et al, 2012; Lee and Mykland, 2012).
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
