Tests for an end-of-sample bubble in financial time series

Astill, Sam; Harvey, David I.; Leybourne, Stephen J.; Taylor, Robert

Abstract

In this paper we examine the issue of detecting explosive behaviour in economic and financial time series when an explosive episode is both ongoing at the end of the sample, and of finite length. We propose a testing strategy based on the sub-sampling method of Andrews (2003), in which a suitable test statistic is calculated on a finite number of end-of-sample observations, with a critical value obtained using sub-sample test statistics calculated on the remaining observations. This approach also has the practical advantage that, by virtue of how the critical values are obtained, it can deliver tests which are robust to, among other things, conditional heteroskedasticity and serial correlation in the driving shocks. We also explore modifications of the raw statistics to account for unconditional heteroskedasticity using studentisation and a White-type correction. We evaluate the finite sample size and power properties of our proposed procedures, and find that they offer promising levels of power, suggesting the possibility for earlier detection of end-of-sample bubble episodes compared to existing procedures.

Citation

Astill, S., Harvey, D. I., Leybourne, S. J., & Taylor, R. (in press). Tests for an end-of-sample bubble in financial time series. Econometric Reviews, 36(6-9), https://doi.org/10.1080/07474938.2017.1307490

• Journal Article Type: Article
• Acceptance Date: Oct 3, 2016
• Online Publication Date: Mar 22, 2017
• Deposit Date: Oct 21, 2016
• Publicly Available Date: Mar 22, 2017
• Journal: Econometric Reviews
• Print ISSN: 0747-4938
• Electronic ISSN: 1532-4168
• Publisher: Taylor and Francis
• Peer Reviewed: Peer Reviewed
• Volume: 36
• Issue: 6-9
• DOI: https://doi.org/10.1080/07474938.2017.1307490
• Keywords: Rational bubble; Explosive autoregression; Right-tailed unit root testing: Sub-sampling
• Public URL: https://nottingham-repository.worktribe.com/output/851852
• Publisher URL: http://www.tandfonline.com/doi/abs/10.1080/07474938.2017.1307490
• Additional Information: “This is an Accepted Manuscript of an article published by Taylor & Francis in Econometric Reviews on 22 March 2017, available online: http://www.tandfonline.com/doi/abs/10.1080/07474938.2017.1307490
• Contract Date: Oct 21, 2016