Bootstrap union tests for unit roots in the presence of nonstationary volatility

S. Smeekes, A.M.R. Taylor*

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

72 Downloads (Pure)


Three important issues surround testing for a unit root in practice: uncertainty as to whether or not a linear deterministic trend is present in the data; uncertainty as to whether the initial condition of the process is (asymptotically) negligible or not, and the possible presence of nonstationary volatility in the data. Assuming homoskedasticity, Harvey, Leybourne, and Taylor (2011, Journal of Econometrics, forthcoming) propose decision rules based on a four-way union of rejections of quasi-differenced (QD) and ordinary least squares (OLS) detrended tests, both with and without a linear trend, to deal with the first two problems. In this paper we first discuss, again under homoskedasticity, how these union tests may be validly bootstrapped using the sieve bootstrap principle combined with either the independent and identically distributed (i.i.d.) or wild bootstrap resampling schemes. This serves to highlight the complications that arise when attempting to bootstrap the union tests. We then demonstrate that in the presence of nonstationary volatility the union test statistics have limit distributions that depend on the form of the volatility process, making tests based on the standard asymptotic critical values or, indeed, the i.i.d. bootstrap principle invalid. We show that wild bootstrap union tests are, however, asymptotically valid in the presence of nonstationary volatility. The wild bootstrap union tests therefore allow for a joint treatment of all three of the aforementioned issues in practice.
Original languageEnglish
Pages (from-to)422-456
Number of pages35
JournalEconometric Theory
Issue number2
Publication statusPublished - 1 Jan 2012


Dive into the research topics of 'Bootstrap union tests for unit roots in the presence of nonstationary volatility'. Together they form a unique fingerprint.

Cite this