Department of Pattern Recognition

(eng): In this paper, we contribute to the literature on international stock market comovement. The novelty of our approach lies in usage of wavelet tools to high- frequency financial market data, which allows us to understand the relationship between stock market returns in a different way. Major part of economic time series analysis is done in time or frequency domain separately. Wavelet analysis can combine these two fundamental approaches, so we can work in time-frequency domain. Using wavelet power spectra and wavelet coherence, we have uncovered interesting dynamics of cross-correlations between Central European and Western European stock markets using high-frequency data. Our findings provide possibility of a new approach to financial risk modeling.