The robustness of modified unit root tests in the presence of GARCH

Steven Cook

Quantitative Finance, 2006, vol. 6, issue 4, 359-363

Abstract: The research of Kim and Schmidt (J. Economet., 1993, 59, 287-300) is extended to examine the properties of modified Dickey-Fuller unit root tests in the presence of generalized autoregressive conditional heteroskedasticity (GARCH). Using Monte Carlo simulation, the properties of the tests are examined for a range of GARCH processes over alternative sample sizes. Oversizing is observed for all tests, with the extent of size distortion driven by the volatility, rather than the persistence, of the underlying GARCH process. While the original Dickey-Fuller test is found to exhibit greater size distortion than the modified tests, the modified tests are found to be substantially oversized when the GARCH process exhibits a high degree of volatility, even for large samples.

Keywords: GARCH; Unit root tests; Size distortion (search for similar items in EconPapers)
Date: 2006
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (9)

Downloads: (external link)
http://www.tandfonline.com/doi/abs/10.1080/14697680600702045 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:quantf:v:6:y:2006:i:4:p:359-363

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/RQUF20

DOI: 10.1080/14697680600702045

Access Statistics for this article

Quantitative Finance is currently edited by Michael Dempster and Jim Gatheral

More articles in Quantitative Finance from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().