Annals of Statistics
- Ann. Statist.
- Volume 38, Number 5 (2010), 3093-3128.
Is Brownian motion necessary to model high-frequency data?
Yacine Aït-Sahalia and Jean Jacod
Abstract
This paper considers the problem of testing for the presence of a continuous part in a semimartingale sampled at high frequency. We provide two tests, one where the null hypothesis is that a continuous component is present, the other where the continuous component is absent, and the model is then driven by a pure jump process. When applied to high-frequency individual stock data, both tests point toward the need to include a continuous component in the model.
Article information
Source
Ann. Statist., Volume 38, Number 5 (2010), 3093-3128.
Dates
First available in Project Euclid: 13 September 2010
Permanent link to this document
https://projecteuclid.org/euclid.aos/1284391759
Digital Object Identifier
doi:10.1214/09-AOS749
Mathematical Reviews number (MathSciNet)
MR2722465
Zentralblatt MATH identifier
1327.62118
Subjects
Primary: 62F12: Asymptotic properties of estimators 62M05: Markov processes: estimation
Secondary: 60H10: Stochastic ordinary differential equations [See also 34F05] 60J60: Diffusion processes [See also 58J65]
Keywords
Semimartingale Brownian motion jumps finite activity infinite activity discrete sampling high frequency
Citation
Aït-Sahalia, Yacine; Jacod, Jean. Is Brownian motion necessary to model high-frequency data?. Ann. Statist. 38 (2010), no. 5, 3093--3128. doi:10.1214/09-AOS749. https://projecteuclid.org/euclid.aos/1284391759