Empirical mode decomposition analysis of two different financial time series and their comparison

Abstract

Analysis of financial time series with,a view to understanding its underlying characteristic features has been the recent focus of scientists and practitioners studying the financial market. One of the key attributes of a time series is its periodicity. Because of their quasi-periodic nature, the financial time series do not reveal their periodicity clearly. One of the recent developments in time signal analysis is the Hilbert–Huang empirical mode decomposition (EMD) method, which elegantly brings out the underlying periodicity of any time-series. Not many efforts have been made to utilise this technique in qualitative analysis of financial time series. In the present study, we have used the EMD technique to analyse two different financial time series, viz., the daily movement of NIFTY index value of National Stock Exchange, India, and that of Hong Kong AOI, Hong Kong Stock Exchange from July 1990 to January 2006. The returns of the two indices are shown to have strikingly similar probability distribution. The IMF phase and amplitude probability distribution of the two indices also reveal striking similarity. This indicates a remarkable similarity of trading behaviour in the two markets. Considering the geographical and political separation of the two, this indeed is an important discovery.