Why Frequency Matters for Unit Root Testing

Tinbergen Institute Discussion Paper No. TI 2004-119/4

17 Pages Posted: 12 Nov 2004

See all articles by H. Peter Boswijk

H. Peter Boswijk

Amsterdam School of Economics; Tinbergen Institute

Franc Klaassen

University of Amsterdam - Research Institute in Economics & Econometrics (RESAM); Tinbergen Institute

Date Written: November 2004

Abstract

It is generally believed that for the power of unit root tests, only the time span and not the observation frequency matters. In this paper, we show that the observation frequency does matter when the high-frequency data display fat tails and volatility clustering, as is typically the case for financial time series such as exchange rate returns. Our claim builds on recent work on unit root and cointegration testing based non-Gaussian likelihood functions. The essential idea is that such methods will yield power gains in the presence of fat tails and persistent volatility clustering, and the strength of these features (and hence the power gains) increases with the observation frequency. This is illustrated using both Monte Carlo simulations and empirical applications to real exchange rates.

Keywords: Fat tails, GARCH, mean reversion, observation frequency, purchasing-power parity, unit roots

JEL Classification: C12, C22, F31

Suggested Citation

Boswijk, H. Peter and Klaassen, Franc, Why Frequency Matters for Unit Root Testing (November 2004). Tinbergen Institute Discussion Paper No. TI 2004-119/4, Available at SSRN: https://ssrn.com/abstract=617302 or http://dx.doi.org/10.2139/ssrn.617302

H. Peter Boswijk (Contact Author)

Amsterdam School of Economics ( email )

Roetersstraat 11
Amsterdam, North Holland 1018 WB
Netherlands

HOME PAGE: http://www.uva.nl/profile/h.p.boswijk

Tinbergen Institute ( email )

Burg. Oudlaan 50
Rotterdam, 3062 PA
Netherlands

Franc Klaassen

University of Amsterdam - Research Institute in Economics & Econometrics (RESAM) ( email )

Roetersstraat 11
Amsterdam
Netherlands
+31 20 525 4191 (Phone)
+31 20 525 4254 (Fax)

Tinbergen Institute ( email )

Burg. Oudlaan 50
Rotterdam, 3062 PA
Netherlands

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
127
Abstract Views
943
rank
263,934
PlumX Metrics