Nonlinear Noise Estimation in International Capital Markets

Costas Siriopoulos () and Alexandros Leontitsis
Additional contact information
Alexandros Leontitsis: University of Kent at Canterbury, U.K.

Multinational Finance Journal, 2002, vol. 6, issue 1, 43-63

Abstract: We analyzed six stock exchange markets through the nonlinear dynamics concept. We used daily data from the Toronto Stock Exchange, NYSE, London Stock Exchange, Hong Kong Stock Market, Tokyo Stock Exchange, and the Singapore Stock Exchange. The period studied is from January 1, 1988 to June 30, 1999. We performed Local Principal Components Analysis in order to estimate the dimension of each underlying attractor. Our main interest is the noise level estimation of each time series. The results indicate weak determinism and strong noise influence. The noise-to-signal ratio for almost all time series is above 50%. Noise is leptokurtic in the eastern stock markets, and mesokurtic in western ones.

Keywords: chaos theory; local principal components analysis; noise estimation; nonlinear dynamics (search for similar items in EconPapers)
JEL-codes: C22 G15 (search for similar items in EconPapers)
Date: 2002
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.mfsociety.org/modules/modDashboard/uplo ... gnbo1vdqhet1her1.pdf
http://www.mfsociety.org/modules/modDashboard/uplo ... ogleScholar/713.html

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:mfj:journl:v:6:y:2002:i:1:p:43-63

Access Statistics for this article

Multinational Finance Journal is currently edited by Panayiotis C. Andreou

More articles in Multinational Finance Journal from Multinational Finance Journal Contact information at EDIRC.
Bibliographic data for series maintained by Theodossiou Panayiotis ().