Accounting for conditional leptokurtosis and closing days effects in FIGARCH models of daily exchange rates

Michel Beine, Sébastien Laurent, Christelle Lecourt*

*Corresponding author for this work

Research output: Contribution to journalArticle

33 Citations (Scopus)

Abstract

This paper, estimates FIGARCH models introduced by Baillie et al. (1996a) for the four major daily exchange rates against the USD (DEM, FRF, YEN and the GBP). The former contributions are extended by accounting for the observed kurtosis through a Student-t based maximum likelihood estimation and by including variables capturing the effect of closing days. These estimations suggest that the introduction of these features improves the goodness of fit properties of the model on the one hand, and may lead to different interest parameters estimates on the other hand. In particular, it is shown that in the case of the DEM, volatility shocks may display much less persistence than documented by previous studies. Finally, it is shown that an ARFIMA-FIGARCH framework turns out to be relevant for all the currencies (except the GBP), without inducing any significant changes in the inference of the stochastic volatility process.

Original languageEnglish
Pages (from-to)589-600
Number of pages12
JournalApplied Financial Economics
Volume12
Issue number8
DOIs
Publication statusPublished - 2002

Fingerprint Dive into the research topics of 'Accounting for conditional leptokurtosis and closing days effects in FIGARCH models of daily exchange rates'. Together they form a unique fingerprint.

  • Cite this