Measuring stock market resiliency with Discrete Fourier Transform for high frequency data

Abstract

In this paper, we investigate market resiliency as one of the stock market liquidity dimensions. A new methodology for stock resiliency measurement based on Discrete Fourier Transform (DFT) for high-frequency intraday data is introduced. The known disadvantage of DFT is signal leakage. Therefore, the modified formula for resiliency proxy that decreases the signal leakage impact by filtering is utilized. Three alternative window functions are employed: (1) the Hamming window, (2) the Kaiser window, and (3) the SR785 Flat-Top window. Furthermore, there is provided statistical analysis of the results, including its significance and some additional properties. The findings of empirical experiments for real-data from the Warsaw Stock Exchange reveal that the results rather turn out to be robust to the choice of the window filter. Thus, the DFT approach might be considered an auspicious resiliency proxy with an intuitive base.