Evidence of Multifractality from Emerging European Stock Markets

Abstract

We test for the presence of multifractality in the daily returns of the three most important stock market indices from Central and Eastern Europe, Czech PX, Hungarian BUX and Polish WIG using the Empirical Mode Decomposition based Multifractal Detrended Fluctuation Analysis. We found that the global Hurst coefficient varies with the q coefficient and that there is multifractality evidenced through the multifractal spectrum. The exercise is replicated for the sample around the high volatility period corresponding to the last global financial crisis. Although no direct link has been found between the crisis and the multifractal spectrum, the crisis was found to influence the overall shape as quantified through the norm of the multifractal spectrum.

Evidence of multifractality from CEE exchange rates against Euro

“…It is interesting to note that in Ref. [10] where the MF-DFA method is used within the context of CEE based stock market indices, the global Hurst coefficient varies with the q coefficient. There is multifractality evidenced through the multifractal spectrum.…”

“…This methodology, known under the name of empirical mode decomposition (EMD) will be employed in the MF-DFA method and to our knowledge, it has never been applied to (FX) exchange rate time series. We note that in recent work Caraiani [10] uses the MF-DFA method within the context of CEE based stock market indices. We also hasten to add that work on the multifractal analysis of FX rates has already been performed.…”

Multifractal characteristics of external anal sphincter based on sEMG signals

“…Our analysis was branched into standard DFA algorithm and non-standard one based on EMD technique. The former method uses the least-square estimation of the order m. The latter utilizes the fact that the residual r n (3) represents the local trend, thus the standard polynomial fit (DFA) can be replaced by a residuum for each segment [25]. An example of local trends calculated with both methods is presented on Fig.1 for the segment size s = 64.…”

Fractal Analysis of Deep Ocean Current Speed Time Series

“…Hence, it is important to use methods capable of removing the effects of possible trends in the series, such as the DFA and MFDFA, which are well-established methods for determining the scaling of long-term correlation in presence of polynomial trends (Kantelhardt et al 2002;Bashan et al 2008;Caraiani 2012).…”